From c8cdaf998df221b01134a051aba38c570105061b Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Mon, 10 Mar 2008 04:30:37 -0400 Subject: [IPV4,IPV6]: Share cork.rt between IPv4 and IPv6. Signed-off-by: YOSHIFUJI Hideaki --- include/linux/ipv6.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/ipv6.h') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 4aaefc349a4b..2102d8b67c01 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -315,7 +315,6 @@ struct ipv6_pinfo { struct sk_buff *pktoptions; struct { struct ipv6_txoptions *opt; - struct rt6_info *rt; int hop_limit; int tclass; } cork; -- cgit v1.2.3 From 4725474584d6aa2f07b3d47442dfbc4f6544f65e Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Mon, 10 Mar 2008 04:41:33 -0400 Subject: [IPV6]: Convert cork.hop_limit and cork.tclass into u8 instead of int. Values of those fields are always between 0 and 255 (inclusive), so use u8 and save some memory on 32bit systems. Signed-off-by: YOSHIFUJI Hideaki --- include/linux/ipv6.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux/ipv6.h') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 2102d8b67c01..9b59e37afad9 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -315,8 +315,8 @@ struct ipv6_pinfo { struct sk_buff *pktoptions; struct { struct ipv6_txoptions *opt; - int hop_limit; - int tclass; + u8 hop_limit; + u8 tclass; } cork; }; -- cgit v1.2.3 From 1d5d236d309ab90fa6aedf712f586b3595721373 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Mon, 10 Mar 2008 10:56:55 -0400 Subject: [IPV6]: Use bitfields for hop_limit and mcast_hops. Save some bits for future extensions. Signed-off-by: YOSHIFUJI Hideaki --- include/linux/ipv6.h | 28 ++++++++++++++++++++++++---- 1 file changed, 24 insertions(+), 4 deletions(-) (limited to 'include/linux/ipv6.h') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 9b59e37afad9..87ae4e389ce1 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -274,8 +274,29 @@ struct ipv6_pinfo { __be32 flow_label; __u32 frag_size; - __s16 hop_limit; - __s16 mcast_hops; + + /* + * Packed in 16bits. + * Omit one shift by by putting the signed field at MSB. + */ +#if defined(__BIG_ENDIAN_BITFIELD) + __s16 hop_limit:9; + __u16 __unused_1:7; +#else + __u16 __unused_1:7; + __s16 hop_limit:9; +#endif + +#if defined(__BIG_ENDIAN_BITFIELD) + /* Packed in 16bits. */ + __s16 mcast_hops:9; + __u16 __unused_2:6, + mc_loop:1; +#else + __u16 mc_loop:1, + __unused_2:6; + __s16 mcast_hops:9; +#endif int mcast_oif; /* pktoption flags */ @@ -298,8 +319,7 @@ struct ipv6_pinfo { } rxopt; /* sockopt flags */ - __u8 mc_loop:1, - recverr:1, + __u8 recverr:1, sndflow:1, pmtudisc:2, ipv6only:1; -- cgit v1.2.3 From 7cbca67c073263c179f605bdbbdc565ab29d801d Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Tue, 25 Mar 2008 09:37:42 +0900 Subject: [IPV6]: Support Source Address Selection API (RFC5014). Signed-off-by: YOSHIFUJI Hideaki --- include/linux/in6.h | 11 +++++++ include/linux/ipv6.h | 6 +++- include/net/addrconf.h | 1 + include/net/ip6_route.h | 9 ++++-- net/ipv6/addrconf.c | 17 +++++++++-- net/ipv6/fib6_rules.c | 12 +++++++- net/ipv6/ip6_output.c | 4 ++- net/ipv6/ipv6_sockglue.c | 78 ++++++++++++++++++++++++++++++++++++++++++++++++ net/ipv6/ndisc.c | 4 ++- net/ipv6/route.c | 11 ++++++- net/ipv6/xfrm6_policy.c | 2 +- net/sctp/ipv6.c | 4 ++- 12 files changed, 146 insertions(+), 13 deletions(-) (limited to 'include/linux/ipv6.h') diff --git a/include/linux/in6.h b/include/linux/in6.h index 2a61c82af115..f674000c6c99 100644 --- a/include/linux/in6.h +++ b/include/linux/in6.h @@ -249,4 +249,15 @@ struct in6_flowlabel_req * IP6T_SO_GET_REVISION_TARGET 69 */ +/* RFC5014: Source address selection */ +#define IPV6_ADDR_PREFERENCES 72 + +#define IPV6_PREFER_SRC_TMP 0x0001 +#define IPV6_PREFER_SRC_PUBLIC 0x0002 +#define IPV6_PREFER_SRC_PUBTMP_DEFAULT 0x0100 +#define IPV6_PREFER_SRC_COA 0x0004 +#define IPV6_PREFER_SRC_HOME 0x0400 +#define IPV6_PREFER_SRC_CGA 0x0008 +#define IPV6_PREFER_SRC_NONCGA 0x0800 + #endif diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 87ae4e389ce1..c9ba0da16ce9 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -322,7 +322,11 @@ struct ipv6_pinfo { __u8 recverr:1, sndflow:1, pmtudisc:2, - ipv6only:1; + ipv6only:1, + srcprefs:3; /* 001: prefer temporary address + * 010: prefer public address + * 100: prefer care-of address + */ __u8 tclass; __u32 dst_cookie; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index edcb4bbaab7d..c9276c72764d 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -78,6 +78,7 @@ extern struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, extern int ipv6_dev_get_saddr(struct net_device *dev, struct in6_addr *daddr, + unsigned int srcprefs, struct in6_addr *saddr); extern int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 5c3b67c86aef..3ae6799c2b14 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -30,9 +30,12 @@ struct route_info { #include #include -#define RT6_LOOKUP_F_IFACE 0x1 -#define RT6_LOOKUP_F_REACHABLE 0x2 -#define RT6_LOOKUP_F_HAS_SADDR 0x4 +#define RT6_LOOKUP_F_IFACE 0x00000001 +#define RT6_LOOKUP_F_REACHABLE 0x00000002 +#define RT6_LOOKUP_F_HAS_SADDR 0x00000004 +#define RT6_LOOKUP_F_SRCPREF_TMP 0x00000008 +#define RT6_LOOKUP_F_SRCPREF_PUBLIC 0x00000010 +#define RT6_LOOKUP_F_SRCPREF_COA 0x00000020 extern struct rt6_info *ip6_null_entry; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 787e90af166c..89954885dee1 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -909,6 +909,7 @@ struct ipv6_saddr_dst { int ifindex; int scope; int label; + unsigned int prefs; }; static inline int ipv6_saddr_preferred(int type) @@ -984,9 +985,12 @@ static int ipv6_get_saddr_eval(struct ipv6_saddr_score *score, break; #ifdef CONFIG_IPV6_MIP6 case IPV6_SADDR_RULE_HOA: + { /* Rule 4: Prefer home address */ - ret = !!(score->ifa->flags & IFA_F_HOMEADDRESS); + int prefhome = !(dst->prefs & IPV6_PREFER_SRC_COA); + ret = !(score->ifa->flags & IFA_F_HOMEADDRESS) ^ prefhome; break; + } #endif case IPV6_SADDR_RULE_OIF: /* Rule 5: Prefer outgoing interface */ @@ -1000,11 +1004,16 @@ static int ipv6_get_saddr_eval(struct ipv6_saddr_score *score, break; #ifdef CONFIG_IPV6_PRIVACY case IPV6_SADDR_RULE_PRIVACY: + { /* Rule 7: Prefer public address * Note: prefer temprary address if use_tempaddr >= 2 */ - ret = (!(score->ifa->flags & IFA_F_TEMPORARY)) ^ (score->ifa->idev->cnf.use_tempaddr >= 2); + int preftmp = dst->prefs & (IPV6_PREFER_SRC_PUBLIC|IPV6_PREFER_SRC_TMP) ? + !!(dst->prefs & IPV6_PREFER_SRC_TMP) : + score->ifa->idev->cnf.use_tempaddr >= 2; + ret = (!(score->ifa->flags & IFA_F_TEMPORARY)) ^ preftmp; break; + } #endif case IPV6_SADDR_RULE_ORCHID: /* Rule 8-: Prefer ORCHID vs ORCHID or @@ -1030,7 +1039,8 @@ out: } int ipv6_dev_get_saddr(struct net_device *dst_dev, - struct in6_addr *daddr, struct in6_addr *saddr) + struct in6_addr *daddr, unsigned int prefs, + struct in6_addr *saddr) { struct ipv6_saddr_score scores[2], *score = &scores[0], *hiscore = &scores[1]; @@ -1044,6 +1054,7 @@ int ipv6_dev_get_saddr(struct net_device *dst_dev, dst.ifindex = dst_dev ? dst_dev->ifindex : 0; dst.scope = __ipv6_addr_src_scope(dst_type); dst.label = ipv6_addr_label(daddr, dst_type, dst.ifindex); + dst.prefs = prefs; hiscore->rule = -1; hiscore->ifa = NULL; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 55137408f054..e7a7fe26cebf 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -84,8 +84,18 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, if ((rule->flags & FIB_RULE_FIND_SADDR) && r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) { struct in6_addr saddr; + unsigned int srcprefs = 0; + + if (flags & RT6_LOOKUP_F_SRCPREF_TMP) + srcprefs |= IPV6_PREFER_SRC_TMP; + if (flags & RT6_LOOKUP_F_SRCPREF_PUBLIC) + srcprefs |= IPV6_PREFER_SRC_PUBLIC; + if (flags & RT6_LOOKUP_F_SRCPREF_COA) + srcprefs |= IPV6_PREFER_SRC_COA; + if (ipv6_dev_get_saddr(ip6_dst_idev(&rt->u.dst)->dev, - &flp->fl6_dst, &saddr)) + &flp->fl6_dst, srcprefs, + &saddr)) goto again; if (!ipv6_prefix_equal(&saddr, &r->src.addr, r->src.plen)) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2a4f08c8a02d..d34aa61353bb 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -920,7 +920,9 @@ static int ip6_dst_lookup_tail(struct sock *sk, if (ipv6_addr_any(&fl->fl6_src)) { err = ipv6_dev_get_saddr(ip6_dst_idev(*dst)->dev, - &fl->fl6_dst, &fl->fl6_src); + &fl->fl6_dst, + sk ? inet6_sk(sk)->srcprefs : 0, + &fl->fl6_src); if (err) goto out_err_release; } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 8e29fb1d1df6..dc6695cc5767 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -617,7 +617,67 @@ done: retv = xfrm_user_policy(sk, optname, optval, optlen); break; + case IPV6_ADDR_PREFERENCES: + { + unsigned int pref = 0; + unsigned int prefmask = ~0; + + retv = -EINVAL; + + /* check PUBLIC/TMP/PUBTMP_DEFAULT conflicts */ + switch (val & (IPV6_PREFER_SRC_PUBLIC| + IPV6_PREFER_SRC_TMP| + IPV6_PREFER_SRC_PUBTMP_DEFAULT)) { + case IPV6_PREFER_SRC_PUBLIC: + pref |= IPV6_PREFER_SRC_PUBLIC; + break; + case IPV6_PREFER_SRC_TMP: + pref |= IPV6_PREFER_SRC_TMP; + break; + case IPV6_PREFER_SRC_PUBTMP_DEFAULT: + break; + case 0: + goto pref_skip_pubtmp; + default: + goto e_inval; + } + + prefmask &= ~(IPV6_PREFER_SRC_PUBLIC| + IPV6_PREFER_SRC_TMP); +pref_skip_pubtmp: + + /* check HOME/COA conflicts */ + switch (val & (IPV6_PREFER_SRC_HOME|IPV6_PREFER_SRC_COA)) { + case IPV6_PREFER_SRC_HOME: + break; + case IPV6_PREFER_SRC_COA: + pref |= IPV6_PREFER_SRC_COA; + case 0: + goto pref_skip_coa; + default: + goto e_inval; + } + + prefmask &= ~IPV6_PREFER_SRC_COA; +pref_skip_coa: + + /* check CGA/NONCGA conflicts */ + switch (val & (IPV6_PREFER_SRC_CGA|IPV6_PREFER_SRC_NONCGA)) { + case IPV6_PREFER_SRC_CGA: + case IPV6_PREFER_SRC_NONCGA: + case 0: + break; + default: + goto e_inval; + } + + np->srcprefs = (np->srcprefs & prefmask) | pref; + retv = 0; + + break; + } } + release_sock(sk); return retv; @@ -932,6 +992,24 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, val = np->sndflow; break; + case IPV6_ADDR_PREFERENCES: + val = 0; + + if (np->srcprefs & IPV6_PREFER_SRC_TMP) + val |= IPV6_PREFER_SRC_TMP; + else if (np->srcprefs & IPV6_PREFER_SRC_PUBLIC) + val |= IPV6_PREFER_SRC_PUBLIC; + else { + /* XXX: should we return system default? */ + val |= IPV6_PREFER_SRC_PUBTMP_DEFAULT; + } + + if (np->srcprefs & IPV6_PREFER_SRC_COA) + val |= IPV6_PREFER_SRC_COA; + else + val |= IPV6_PREFER_SRC_HOME; + break; + default: return -ENOPROTOOPT; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index e7d8e74704c1..3f68a6eae7b2 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -546,7 +546,9 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, override = 0; in6_ifa_put(ifp); } else { - if (ipv6_dev_get_saddr(dev, daddr, &tmpaddr)) + if (ipv6_dev_get_saddr(dev, daddr, + inet6_sk(dev->nd_net->ipv6.ndisc_sk)->srcprefs, + &tmpaddr)) return; src_addr = &tmpaddr; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index aa3f08718e44..06faa46920e1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -782,6 +782,15 @@ struct dst_entry * ip6_route_output(struct net *net, struct sock *sk, if (!ipv6_addr_any(&fl->fl6_src)) flags |= RT6_LOOKUP_F_HAS_SADDR; + else if (sk) { + unsigned int prefs = inet6_sk(sk)->srcprefs; + if (prefs & IPV6_PREFER_SRC_TMP) + flags |= RT6_LOOKUP_F_SRCPREF_TMP; + if (prefs & IPV6_PREFER_SRC_PUBLIC) + flags |= RT6_LOOKUP_F_SRCPREF_PUBLIC; + if (prefs & IPV6_PREFER_SRC_COA) + flags |= RT6_LOOKUP_F_SRCPREF_COA; + } return fib6_rule_lookup(net, fl, flags, ip6_pol_route_output); } @@ -2162,7 +2171,7 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, else if (dst) { struct in6_addr saddr_buf; if (ipv6_dev_get_saddr(ip6_dst_idev(&rt->u.dst)->dev, - dst, &saddr_buf) == 0) + dst, 0, &saddr_buf) == 0) NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index e96dafdc7032..d92d1fceb8cf 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -58,7 +58,7 @@ static int xfrm6_get_saddr(xfrm_address_t *saddr, xfrm_address_t *daddr) return -EHOSTUNREACH; ipv6_dev_get_saddr(ip6_dst_idev(dst)->dev, - (struct in6_addr *)&daddr->a6, + (struct in6_addr *)&daddr->a6, 0, (struct in6_addr *)&saddr->a6); dst_release(dst); return 0; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 46c5b3c5cb99..dc71d0d83753 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -316,7 +316,9 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc, if (!asoc) { ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL, - &daddr->v6.sin6_addr, &saddr->v6.sin6_addr); + &daddr->v6.sin6_addr, + inet6_sk(asoc->base.sk)->srcprefs, + &saddr->v6.sin6_addr); SCTP_DEBUG_PRINTK("saddr from ipv6_get_saddr: " NIP6_FMT "\n", NIP6(saddr->v6.sin6_addr)); return; -- cgit v1.2.3 From 3b1e0a655f8eba44ab1ee2a1068d169ccfb853b9 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Wed, 26 Mar 2008 02:26:21 +0900 Subject: [NET] NETNS: Omit sock->sk_net without CONFIG_NET_NS. Introduce per-sock inlines: sock_net(), sock_net_set() and per-inet_timewait_sock inlines: twsk_net(), twsk_net_set(). Without CONFIG_NET_NS, no namespace other than &init_net exists. Let's explicitly define them to help compiler optimizations. Signed-off-by: YOSHIFUJI Hideaki --- include/linux/ipv6.h | 4 ++-- include/net/inet_hashtables.h | 8 ++++---- include/net/inet_timewait_sock.h | 18 ++++++++++++++++++ include/net/route.h | 4 ++-- include/net/sock.h | 24 ++++++++++++++++++++++-- net/atm/svc.c | 2 +- net/ax25/af_ax25.c | 2 +- net/bluetooth/l2cap.c | 2 +- net/bluetooth/rfcomm/sock.c | 2 +- net/bluetooth/sco.c | 2 +- net/bridge/br_netlink.c | 4 ++-- net/core/fib_rules.c | 6 +++--- net/core/neighbour.c | 10 +++++----- net/core/rtnetlink.c | 12 ++++++------ net/core/sock.c | 10 +++++----- net/decnet/af_decnet.c | 2 +- net/decnet/dn_dev.c | 6 +++--- net/decnet/dn_fib.c | 4 ++-- net/decnet/dn_route.c | 4 ++-- net/decnet/dn_table.c | 2 +- net/ipv4/af_inet.c | 6 +++--- net/ipv4/devinet.c | 6 +++--- net/ipv4/fib_frontend.c | 8 ++++---- net/ipv4/fib_rules.c | 2 +- net/ipv4/igmp.c | 14 +++++++------- net/ipv4/inet_connection_sock.c | 4 ++-- net/ipv4/inet_hashtables.c | 8 ++++---- net/ipv4/inet_timewait_sock.c | 2 +- net/ipv4/ip_input.c | 2 +- net/ipv4/ip_output.c | 4 ++-- net/ipv4/ip_sockglue.c | 6 +++--- net/ipv4/ipmr.c | 4 ++-- net/ipv4/netfilter/arp_tables.c | 16 ++++++++-------- net/ipv4/netfilter/ip_tables.c | 16 ++++++++-------- net/ipv4/raw.c | 12 ++++++------ net/ipv4/route.c | 4 ++-- net/ipv4/tcp_ipv4.c | 14 +++++++------- net/ipv4/udp.c | 16 ++++++++-------- net/ipv6/addrconf.c | 10 +++++----- net/ipv6/addrlabel.c | 6 +++--- net/ipv6/af_inet6.c | 4 ++-- net/ipv6/fib6_rules.c | 2 +- net/ipv6/icmp.c | 2 +- net/ipv6/inet6_hashtables.c | 4 ++-- net/ipv6/ip6_fib.c | 2 +- net/ipv6/ip6_output.c | 2 +- net/ipv6/ipv6_sockglue.c | 2 +- net/ipv6/mcast.c | 12 ++++++------ net/ipv6/netfilter/ip6_tables.c | 16 ++++++++-------- net/ipv6/raw.c | 6 +++--- net/ipv6/route.c | 4 ++-- net/ipv6/tcp_ipv6.c | 2 +- net/ipv6/udp.c | 4 ++-- net/irda/af_irda.c | 2 +- net/llc/llc_conn.c | 2 +- net/netfilter/nf_sockopt.c | 2 +- net/netlink/af_netlink.c | 30 +++++++++++++++--------------- net/netrom/af_netrom.c | 2 +- net/packet/af_packet.c | 28 ++++++++++++++-------------- net/rose/af_rose.c | 2 +- net/sched/act_api.c | 4 ++-- net/sched/cls_api.c | 4 ++-- net/sched/sch_api.c | 10 +++++----- net/sctp/ipv6.c | 2 +- net/sctp/protocol.c | 2 +- net/socket.c | 4 ++-- net/tipc/socket.c | 2 +- net/unix/af_unix.c | 20 ++++++++++---------- net/x25/af_x25.c | 2 +- 69 files changed, 253 insertions(+), 215 deletions(-) (limited to 'include/linux/ipv6.h') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index c9ba0da16ce9..b90d3d461d4e 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -481,7 +481,7 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) #endif /* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */ #define INET6_MATCH(__sk, __net, __hash, __saddr, __daddr, __ports, __dif)\ - (((__sk)->sk_hash == (__hash)) && ((__sk)->sk_net == (__net)) && \ + (((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net) && \ ((*((__portpair *)&(inet_sk(__sk)->dport))) == (__ports)) && \ ((__sk)->sk_family == AF_INET6) && \ ipv6_addr_equal(&inet6_sk(__sk)->daddr, (__saddr)) && \ @@ -489,7 +489,7 @@ static inline struct raw6_sock *raw6_sk(const struct sock *sk) (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) #define INET6_TW_MATCH(__sk, __net, __hash, __saddr, __daddr, __ports, __dif) \ - (((__sk)->sk_hash == (__hash)) && ((__sk)->sk_net == (__net)) && \ + (((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net) && \ (*((__portpair *)&(inet_twsk(__sk)->tw_dport)) == (__ports)) && \ ((__sk)->sk_family == PF_INET6) && \ (ipv6_addr_equal(&inet6_twsk(__sk)->tw_v6_daddr, (__saddr))) && \ diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index d99c1ba2ece0..5525227c5e92 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -314,25 +314,25 @@ typedef __u64 __bitwise __addrpair; ((__force __u64)(__be32)(__saddr))); #endif /* __BIG_ENDIAN */ #define INET_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif)\ - (((__sk)->sk_hash == (__hash)) && ((__sk)->sk_net == (__net)) && \ + (((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net) && \ ((*((__addrpair *)&(inet_sk(__sk)->daddr))) == (__cookie)) && \ ((*((__portpair *)&(inet_sk(__sk)->dport))) == (__ports)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) #define INET_TW_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif)\ - (((__sk)->sk_hash == (__hash)) && ((__sk)->sk_net == (__net)) && \ + (((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net) && \ ((*((__addrpair *)&(inet_twsk(__sk)->tw_daddr))) == (__cookie)) && \ ((*((__portpair *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) #else /* 32-bit arch */ #define INET_ADDR_COOKIE(__name, __saddr, __daddr) #define INET_MATCH(__sk, __net, __hash, __cookie, __saddr, __daddr, __ports, __dif) \ - (((__sk)->sk_hash == (__hash)) && ((__sk)->sk_net == (__net)) && \ + (((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net) && \ (inet_sk(__sk)->daddr == (__saddr)) && \ (inet_sk(__sk)->rcv_saddr == (__daddr)) && \ ((*((__portpair *)&(inet_sk(__sk)->dport))) == (__ports)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) #define INET_TW_MATCH(__sk, __net, __hash,__cookie, __saddr, __daddr, __ports, __dif) \ - (((__sk)->sk_hash == (__hash)) && ((__sk)->sk_net == (__net)) && \ + (((__sk)->sk_hash == (__hash)) && sock_net((__sk)) == (__net) && \ (inet_twsk(__sk)->tw_daddr == (__saddr)) && \ (inet_twsk(__sk)->tw_rcv_saddr == (__daddr)) && \ ((*((__portpair *)&(inet_twsk(__sk)->tw_dport))) == (__ports)) && \ diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 296547bfb0b7..07fe0d1a4f03 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -207,4 +207,22 @@ extern void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo, const int timewait_len); extern void inet_twsk_deschedule(struct inet_timewait_sock *tw, struct inet_timewait_death_row *twdr); + +static inline +struct net *twsk_net(const struct inet_timewait_sock *twsk) +{ +#ifdef CONFIG_NET_NS + return twsk->tw_net; +#else + return &init_net; +#endif +} + +static inline +void twsk_net_set(struct inet_timewait_sock *twsk, const struct net *net) +{ +#ifdef CONFIG_NET_NS + twsk->tw_net = net; +#endif +} #endif /* _INET_TIMEWAIT_SOCK_ */ diff --git a/include/net/route.h b/include/net/route.h index 28dba925663c..c6338802e8f1 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -160,7 +160,7 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst, .dport = dport } } }; int err; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); if (!dst || !src) { err = __ip_route_output_key(net, rp, &fl); if (err) @@ -188,7 +188,7 @@ static inline int ip_route_newports(struct rtable **rp, u8 protocol, ip_rt_put(*rp); *rp = NULL; security_sk_classify_flow(sk, &fl); - return ip_route_output_flow(sk->sk_net, rp, &fl, sk, 0); + return ip_route_output_flow(sock_net(sk), rp, &fl, sk, 0); } return 0; } diff --git a/include/net/sock.h b/include/net/sock.h index b433b1ed203d..7e0d4a0c4d12 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -126,7 +126,9 @@ struct sock_common { atomic_t skc_refcnt; unsigned int skc_hash; struct proto *skc_prot; +#ifdef CONFIG_NET_NS struct net *skc_net; +#endif }; /** @@ -1345,6 +1347,24 @@ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, int copied_e } #endif +static inline +struct net *sock_net(const struct sock *sk) +{ +#ifdef CONFIG_NET_NS + return sk->sk_net; +#else + return &init_net; +#endif +} + +static inline +void sock_net_set(struct sock *sk, const struct net *net) +{ +#ifdef CONFIG_NET_NS + sk->sk_net = net; +#endif +} + /* * Kernel sockets, f.e. rtnl or icmp_socket, are a part of a namespace. * They should not hold a referrence to a namespace in order to allow @@ -1353,8 +1373,8 @@ static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, int copied_e */ static inline void sk_change_net(struct sock *sk, struct net *net) { - put_net(sk->sk_net); - sk->sk_net = net; + put_net(sock_net(sk)); + sock_net_set(sk, net); } extern void sock_enable_timestamp(struct sock *sk); diff --git a/net/atm/svc.c b/net/atm/svc.c index daf9a48a7db0..de1e4f2f3a43 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -326,7 +326,7 @@ static int svc_accept(struct socket *sock,struct socket *newsock,int flags) lock_sock(sk); - error = svc_create(sk->sk_net, newsock,0); + error = svc_create(sock_net(sk), newsock,0); if (error) goto out; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index ee9dd83e7561..2712544cf0ca 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -869,7 +869,7 @@ struct sock *ax25_make_new(struct sock *osk, struct ax25_dev *ax25_dev) struct sock *sk; ax25_cb *ax25, *oax25; - sk = sk_alloc(osk->sk_net, PF_AX25, GFP_ATOMIC, osk->sk_prot); + sk = sk_alloc(sock_net(osk), PF_AX25, GFP_ATOMIC, osk->sk_prot); if (sk == NULL) return NULL; diff --git a/net/bluetooth/l2cap.c b/net/bluetooth/l2cap.c index 34f8bf98bc05..6b995ac832f5 100644 --- a/net/bluetooth/l2cap.c +++ b/net/bluetooth/l2cap.c @@ -1499,7 +1499,7 @@ static inline int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hd goto response; } - sk = l2cap_sock_alloc(parent->sk_net, NULL, BTPROTO_L2CAP, GFP_ATOMIC); + sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, GFP_ATOMIC); if (!sk) goto response; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index c46d51035e77..c103fa02893b 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -868,7 +868,7 @@ int rfcomm_connect_ind(struct rfcomm_session *s, u8 channel, struct rfcomm_dlc * goto done; } - sk = rfcomm_sock_alloc(parent->sk_net, NULL, BTPROTO_RFCOMM, GFP_ATOMIC); + sk = rfcomm_sock_alloc(sock_net(parent), NULL, BTPROTO_RFCOMM, GFP_ATOMIC); if (!sk) goto done; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index b91d3c81a73c..2a5953b4405d 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -803,7 +803,7 @@ static void sco_conn_ready(struct sco_conn *conn) bh_lock_sock(parent); - sk = sco_sock_alloc(parent->sk_net, NULL, BTPROTO_SCO, GFP_ATOMIC); + sk = sco_sock_alloc(sock_net(parent), NULL, BTPROTO_SCO, GFP_ATOMIC); if (!sk) { bh_unlock_sock(parent); goto done; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index f5d69336d97b..f155e6ce8a21 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -108,7 +108,7 @@ errout: */ static int br_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct net_device *dev; int idx; @@ -140,7 +140,7 @@ skip: */ static int br_rtm_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; struct nlattr *protinfo; struct net_device *dev; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 942be93a2eb0..540c07283e31 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -214,7 +214,7 @@ errout: static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; struct fib_rule *rule, *r, *last = NULL; @@ -352,7 +352,7 @@ errout: static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); struct fib_rules_ops *ops = NULL; struct fib_rule *rule, *tmp; @@ -534,7 +534,7 @@ skip: static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct fib_rules_ops *ops; int idx = 0, family; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index c978bd1cd659..065fbac7ecd3 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1478,7 +1478,7 @@ int neigh_table_clear(struct neigh_table *tbl) static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *dst_attr; struct neigh_table *tbl; @@ -1544,7 +1544,7 @@ out: static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; struct neigh_table *tbl; @@ -1812,7 +1812,7 @@ static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = { static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct neigh_table *tbl; struct ndtmsg *ndtmsg; struct nlattr *tb[NDTA_MAX+1]; @@ -1937,7 +1937,7 @@ errout: static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); int family, tidx, nidx = 0; int tbl_skip = cb->args[0]; int neigh_skip = cb->args[1]; @@ -2037,7 +2037,7 @@ static void neigh_update_notify(struct neighbour *neigh) static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb) { - struct net * net = skb->sk->sk_net; + struct net * net = sock_net(skb->sk); struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 09250a0800f6..da99ac0871bf 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -662,7 +662,7 @@ nla_put_failure: static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); int idx; int s_idx = cb->args[0]; struct net_device *dev; @@ -879,7 +879,7 @@ errout: static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; struct net_device *dev; int err; @@ -921,7 +921,7 @@ errout: static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); const struct rtnl_link_ops *ops; struct net_device *dev; struct ifinfomsg *ifm; @@ -1000,7 +1000,7 @@ err: static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); const struct rtnl_link_ops *ops; struct net_device *dev; struct ifinfomsg *ifm; @@ -1132,7 +1132,7 @@ replay: static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; struct nlattr *tb[IFLA_MAX+1]; struct net_device *dev = NULL; @@ -1227,7 +1227,7 @@ static int rtattr_max; static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); rtnl_doit_func doit; int sz_idx, kind; int min_len; diff --git a/net/core/sock.c b/net/core/sock.c index b1a6ed4d33c1..3ee95060dbd0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -372,7 +372,7 @@ static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); char devname[IFNAMSIZ]; int index; @@ -958,7 +958,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, */ sk->sk_prot = sk->sk_prot_creator = prot; sock_lock_init(sk); - sk->sk_net = get_net(net); + sock_net_set(sk, get_net(net)); } return sk; @@ -983,7 +983,7 @@ void sk_free(struct sock *sk) printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n", __func__, atomic_read(&sk->sk_omem_alloc)); - put_net(sk->sk_net); + put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); } @@ -1001,7 +1001,7 @@ void sk_release_kernel(struct sock *sk) sock_hold(sk); sock_release(sk->sk_socket); - sk->sk_net = get_net(&init_net); + sock_net_set(sk, get_net(&init_net)); sock_put(sk); } EXPORT_SYMBOL(sk_release_kernel); @@ -1017,7 +1017,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) sock_copy(newsk, sk); /* SANITY */ - get_net(newsk->sk_net); + get_net(sock_net(newsk)); sk_node_init(&newsk->sk_node); sock_lock_init(newsk); bh_lock_sock(newsk); diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 3554fb3d251c..fc2efe899e91 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1094,7 +1094,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags) cb = DN_SKB_CB(skb); sk->sk_ack_backlog--; - newsk = dn_alloc_sock(sk->sk_net, newsock, sk->sk_allocation); + newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation); if (newsk == NULL) { release_sock(sk); kfree_skb(skb); diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index 1bbfce5f7a2d..2f0ac3c3eb71 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -625,7 +625,7 @@ static const struct nla_policy dn_ifa_policy[IFA_MAX+1] = { static int dn_nl_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct nlattr *tb[IFA_MAX+1]; struct dn_dev *dn_db; struct ifaddrmsg *ifm; @@ -663,7 +663,7 @@ errout: static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct nlattr *tb[IFA_MAX+1]; struct net_device *dev; struct dn_dev *dn_db; @@ -779,7 +779,7 @@ errout: static int dn_nl_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); int idx, dn_idx = 0, skip_ndevs, skip_naddr; struct net_device *dev; struct dn_dev *dn_db; diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 4aa9a423e606..27ea2e9b080a 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -504,7 +504,7 @@ static int dn_fib_check_attr(struct rtmsg *r, struct rtattr **rta) static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct dn_fib_table *tb; struct rtattr **rta = arg; struct rtmsg *r = NLMSG_DATA(nlh); @@ -524,7 +524,7 @@ static int dn_fib_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void * static int dn_fib_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct dn_fib_table *tb; struct rtattr **rta = arg; struct rtmsg *r = NLMSG_DATA(nlh); diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 0a46b6c10e51..2f665a516476 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -1512,7 +1512,7 @@ rtattr_failure: */ static int dn_cache_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = in_skb->sk->sk_net; + struct net *net = sock_net(in_skb->sk); struct rtattr **rta = arg; struct rtmsg *rtm = NLMSG_DATA(nlh); struct dn_route *rt = NULL; @@ -1601,7 +1601,7 @@ out_free: */ int dn_cache_dump(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct dn_route *rt; int h, s_h; int idx, s_idx; diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index e09d915dbd77..3a2830ac89c2 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -463,7 +463,7 @@ static int dn_fib_table_dump(struct dn_fib_table *tb, struct sk_buff *skb, int dn_fib_dump(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); unsigned int h, s_h; unsigned int e = 0, s_e; struct dn_fib_table *tb; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 06cfb0bed631..5882a1316441 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -464,7 +464,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_len < sizeof(struct sockaddr_in)) goto out; - chk_addr_ret = inet_addr_type(sk->sk_net, addr->sin_addr.s_addr); + chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); /* Not specified by any standard per-se, however it breaks too * many applications when removed. It is unfortunate since @@ -802,7 +802,7 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; int err = 0; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); switch (cmd) { case SIOCGSTAMP: @@ -1132,7 +1132,7 @@ int inet_sk_rebuild_header(struct sock *sk) }; security_sk_classify_flow(sk, &fl); - err = ip_route_output_flow(sk->sk_net, &rt, &fl, sk, 0); + err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0); } if (!err) sk_setup_caps(sk, &rt->u.dst); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 823c724a8593..6848e4760f34 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -437,7 +437,7 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct nlattr *tb[IFA_MAX+1]; struct in_device *in_dev; struct ifaddrmsg *ifm; @@ -552,7 +552,7 @@ errout: static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct in_ifaddr *ifa; ASSERT_RTNL(); @@ -1158,7 +1158,7 @@ nla_put_failure: static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); int idx, ip_idx; struct net_device *dev; struct in_device *in_dev; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 0e4b34b07cb5..0f1557a4ac7a 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -583,7 +583,7 @@ errout: static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; @@ -605,7 +605,7 @@ errout: static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct fib_config cfg; struct fib_table *tb; int err; @@ -627,7 +627,7 @@ errout: static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); unsigned int h, s_h; unsigned int e = 0, s_e; struct fib_table *tb; @@ -857,7 +857,7 @@ static void nl_fib_input(struct sk_buff *skb) struct fib_table *tb; u32 pid; - net = skb->sk->sk_net; + net = sock_net(skb->sk); nlh = nlmsg_hdr(skb); if (skb->len < NLMSG_SPACE(0) || skb->len < nlh->nlmsg_len || nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*frn))) diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 19274d01afa4..1fb56876be54 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -137,7 +137,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct nlmsghdr *nlh, struct fib_rule_hdr *frh, struct nlattr **tb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); int err = -EINVAL; struct fib4_rule *rule4 = (struct fib4_rule *) rule; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 682f632bfb77..6250f4239b61 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1762,7 +1762,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) if (!ipv4_is_multicast(addr)) return -EINVAL; - if (sk->sk_net != &init_net) + if (sock_net(sk) != &init_net) return -EPROTONOSUPPORT; rtnl_lock(); @@ -1833,7 +1833,7 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) u32 ifindex; int ret = -EADDRNOTAVAIL; - if (sk->sk_net != &init_net) + if (sock_net(sk) != &init_net) return -EPROTONOSUPPORT; rtnl_lock(); @@ -1881,7 +1881,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct if (!ipv4_is_multicast(addr)) return -EINVAL; - if (sk->sk_net != &init_net) + if (sock_net(sk) != &init_net) return -EPROTONOSUPPORT; rtnl_lock(); @@ -2017,7 +2017,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; - if (sk->sk_net != &init_net) + if (sock_net(sk) != &init_net) return -EPROTONOSUPPORT; rtnl_lock(); @@ -2100,7 +2100,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, if (!ipv4_is_multicast(addr)) return -EINVAL; - if (sk->sk_net != &init_net) + if (sock_net(sk) != &init_net) return -EPROTONOSUPPORT; rtnl_lock(); @@ -2165,7 +2165,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, if (!ipv4_is_multicast(addr)) return -EINVAL; - if (sk->sk_net != &init_net) + if (sock_net(sk) != &init_net) return -EPROTONOSUPPORT; rtnl_lock(); @@ -2252,7 +2252,7 @@ void ip_mc_drop_socket(struct sock *sk) if (inet->mc_list == NULL) return; - if (sk->sk_net != &init_net) + if (sock_net(sk) != &init_net) return; rtnl_lock(); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index d13c5f12bb32..a7fcaf205644 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -85,7 +85,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) struct hlist_node *node; struct inet_bind_bucket *tb; int ret; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); local_bh_disable(); if (!snum) { @@ -333,7 +333,7 @@ struct dst_entry* inet_csk_route_req(struct sock *sk, .dport = ireq->rmt_port } } }; security_req_classify_flow(req, &fl); - if (ip_route_output_flow(sk->sk_net, &rt, &fl, sk, 0)) { + if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0)) { IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); return NULL; } diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 8cd1ad9b9111..1064111e5b96 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -139,7 +139,7 @@ static struct sock *inet_lookup_listener_slow(struct net *net, sk_for_each(sk, node, head) { const struct inet_sock *inet = inet_sk(sk); - if (sk->sk_net == net && inet->num == hnum && + if (sock_net(sk) == net && inet->num == hnum && !ipv6_only_sock(sk)) { const __be32 rcv_saddr = inet->rcv_saddr; int score = sk->sk_family == PF_INET ? 1 : 0; @@ -182,7 +182,7 @@ struct sock *__inet_lookup_listener(struct net *net, if (inet->num == hnum && !sk->sk_node.next && (!inet->rcv_saddr || inet->rcv_saddr == daddr) && (sk->sk_family == PF_INET || !ipv6_only_sock(sk)) && - !sk->sk_bound_dev_if && sk->sk_net == net) + !sk->sk_bound_dev_if && sock_net(sk) == net) goto sherry_cache; sk = inet_lookup_listener_slow(net, head, daddr, hnum, dif); } @@ -254,7 +254,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, struct sock *sk2; const struct hlist_node *node; struct inet_timewait_sock *tw; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); prefetch(head->chain.first); write_lock(lock); @@ -406,7 +406,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct inet_bind_hashbucket *head; struct inet_bind_bucket *tb; int ret; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); if (!snum) { int i, remaining, low, high, port; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 717c411a5c6b..f12bc24de46f 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -124,7 +124,7 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, const int stat tw->tw_hash = sk->sk_hash; tw->tw_ipv6only = 0; tw->tw_prot = sk->sk_prot_creator; - tw->tw_net = sk->sk_net; + twsk_net_set(tw, sock_net(sk)); atomic_set(&tw->tw_refcnt, 1); inet_twsk_dead_node_init(tw); __module_get(tw->tw_prot->owner); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 26685c83a146..4be00959b748 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -172,7 +172,7 @@ int ip_call_ra_chain(struct sk_buff *skb) if (sk && inet_sk(sk)->num == protocol && (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex) && - sk->sk_net == dev_net(dev)) { + sock_net(sk) == dev_net(dev)) { if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) { read_unlock(&ip_ra_lock); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 913266cd9902..08349267ceb4 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -351,7 +351,7 @@ int ip_queue_xmit(struct sk_buff *skb, int ipfragok) * itself out. */ security_sk_classify_flow(sk, &fl); - if (ip_route_output_flow(sk->sk_net, &rt, &fl, sk, 0)) + if (ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 0)) goto no_route; } sk_setup_caps(sk, &rt->u.dst); @@ -1382,7 +1382,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar .dport = tcp_hdr(skb)->source } }, .proto = sk->sk_protocol }; security_skb_classify_flow(skb, &fl); - if (ip_route_output_key(sk->sk_net, &rt, &fl)) + if (ip_route_output_key(sock_net(sk), &rt, &fl)) return; } diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index b854431047a4..d6e76f5229cc 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -449,7 +449,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, struct ip_options * opt = NULL; if (optlen > 40 || optlen < 0) goto e_inval; - err = ip_options_get_from_user(sk->sk_net, &opt, + err = ip_options_get_from_user(sock_net(sk), &opt, optval, optlen); if (err) break; @@ -590,13 +590,13 @@ static int do_ip_setsockopt(struct sock *sk, int level, err = 0; break; } - dev = ip_dev_find(sk->sk_net, mreq.imr_address.s_addr); + dev = ip_dev_find(sock_net(sk), mreq.imr_address.s_addr); if (dev) { mreq.imr_ifindex = dev->ifindex; dev_put(dev); } } else - dev = __dev_get_by_index(sk->sk_net, mreq.imr_ifindex); + dev = __dev_get_by_index(sock_net(sk), mreq.imr_ifindex); err = -EADDRNOTAVAIL; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index e54bc1364473..11700a4dcd95 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -849,7 +849,7 @@ static void mrtsock_destruct(struct sock *sk) { rtnl_lock(); if (sk == mroute_socket) { - IPV4_DEVCONF_ALL(sk->sk_net, MC_FORWARDING)--; + IPV4_DEVCONF_ALL(sock_net(sk), MC_FORWARDING)--; write_lock_bh(&mrt_lock); mroute_socket=NULL; @@ -898,7 +898,7 @@ int ip_mroute_setsockopt(struct sock *sk,int optname,char __user *optval,int opt mroute_socket=sk; write_unlock_bh(&mrt_lock); - IPV4_DEVCONF_ALL(sk->sk_net, MC_FORWARDING)++; + IPV4_DEVCONF_ALL(sock_net(sk), MC_FORWARDING)++; } rtnl_unlock(); return ret; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 756bc0e1a7c6..1563f29b5117 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1496,11 +1496,11 @@ static int compat_do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user, switch (cmd) { case ARPT_SO_SET_REPLACE: - ret = compat_do_replace(sk->sk_net, user, len); + ret = compat_do_replace(sock_net(sk), user, len); break; case ARPT_SO_SET_ADD_COUNTERS: - ret = do_add_counters(sk->sk_net, user, len, 1); + ret = do_add_counters(sock_net(sk), user, len, 1); break; default: @@ -1644,10 +1644,10 @@ static int compat_do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, switch (cmd) { case ARPT_SO_GET_INFO: - ret = get_info(sk->sk_net, user, len, 1); + ret = get_info(sock_net(sk), user, len, 1); break; case ARPT_SO_GET_ENTRIES: - ret = compat_get_entries(sk->sk_net, user, len); + ret = compat_get_entries(sock_net(sk), user, len); break; default: ret = do_arpt_get_ctl(sk, cmd, user, len); @@ -1665,11 +1665,11 @@ static int do_arpt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned switch (cmd) { case ARPT_SO_SET_REPLACE: - ret = do_replace(sk->sk_net, user, len); + ret = do_replace(sock_net(sk), user, len); break; case ARPT_SO_SET_ADD_COUNTERS: - ret = do_add_counters(sk->sk_net, user, len, 0); + ret = do_add_counters(sock_net(sk), user, len, 0); break; default: @@ -1689,11 +1689,11 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len switch (cmd) { case ARPT_SO_GET_INFO: - ret = get_info(sk->sk_net, user, len, 0); + ret = get_info(sock_net(sk), user, len, 0); break; case ARPT_SO_GET_ENTRIES: - ret = get_entries(sk->sk_net, user, len); + ret = get_entries(sock_net(sk), user, len); break; case ARPT_SO_GET_REVISION_TARGET: { diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 85a75e186b4b..a819d191e1aa 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1852,11 +1852,11 @@ compat_do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, switch (cmd) { case IPT_SO_SET_REPLACE: - ret = compat_do_replace(sk->sk_net, user, len); + ret = compat_do_replace(sock_net(sk), user, len); break; case IPT_SO_SET_ADD_COUNTERS: - ret = do_add_counters(sk->sk_net, user, len, 1); + ret = do_add_counters(sock_net(sk), user, len, 1); break; default: @@ -1963,10 +1963,10 @@ compat_do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) switch (cmd) { case IPT_SO_GET_INFO: - ret = get_info(sk->sk_net, user, len, 1); + ret = get_info(sock_net(sk), user, len, 1); break; case IPT_SO_GET_ENTRIES: - ret = compat_get_entries(sk->sk_net, user, len); + ret = compat_get_entries(sock_net(sk), user, len); break; default: ret = do_ipt_get_ctl(sk, cmd, user, len); @@ -1985,11 +1985,11 @@ do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) switch (cmd) { case IPT_SO_SET_REPLACE: - ret = do_replace(sk->sk_net, user, len); + ret = do_replace(sock_net(sk), user, len); break; case IPT_SO_SET_ADD_COUNTERS: - ret = do_add_counters(sk->sk_net, user, len, 0); + ret = do_add_counters(sock_net(sk), user, len, 0); break; default: @@ -2010,11 +2010,11 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) switch (cmd) { case IPT_SO_GET_INFO: - ret = get_info(sk->sk_net, user, len, 0); + ret = get_info(sock_net(sk), user, len, 0); break; case IPT_SO_GET_ENTRIES: - ret = get_entries(sk->sk_net, user, len); + ret = get_entries(sock_net(sk), user, len); break; case IPT_SO_GET_REVISION_MATCH: diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 8756d502a47f..be19a4048d7c 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -117,7 +117,7 @@ static struct sock *__raw_v4_lookup(struct net *net, struct sock *sk, sk_for_each_from(sk, node) { struct inet_sock *inet = inet_sk(sk); - if (sk->sk_net == net && inet->num == num && + if (sock_net(sk) == net && inet->num == num && !(inet->daddr && inet->daddr != raddr) && !(inet->rcv_saddr && inet->rcv_saddr != laddr) && !(sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) @@ -499,7 +499,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, ipc.oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { - err = ip_cmsg_send(sk->sk_net, msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc); if (err) goto out; if (ipc.opt) @@ -553,7 +553,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } security_sk_classify_flow(sk, &fl); - err = ip_route_output_flow(sk->sk_net, &rt, &fl, sk, 1); + err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 1); } if (err) goto done; @@ -620,7 +620,7 @@ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (sk->sk_state != TCP_CLOSE || addr_len < sizeof(struct sockaddr_in)) goto out; - chk_addr_ret = inet_addr_type(sk->sk_net, addr->sin_addr.s_addr); + chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); ret = -EADDRNOTAVAIL; if (addr->sin_addr.s_addr && chk_addr_ret != RTN_LOCAL && chk_addr_ret != RTN_MULTICAST && chk_addr_ret != RTN_BROADCAST) @@ -856,7 +856,7 @@ static struct sock *raw_get_first(struct seq_file *seq) struct hlist_node *node; sk_for_each(sk, node, &state->h->ht[state->bucket]) - if (sk->sk_net == state->p.net) + if (sock_net(sk) == state->p.net) goto found; } sk = NULL; @@ -872,7 +872,7 @@ static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk) sk = sk_next(sk); try_again: ; - } while (sk && sk->sk_net != state->p.net); + } while (sk && sock_net(sk) != state->p.net); if (!sk && ++state->bucket < RAW_HTABLE_SIZE) { sk = sk_head(&state->h->ht[state->bucket]); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 7768d718e199..194f5cca3121 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2689,7 +2689,7 @@ nla_put_failure: static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) { - struct net *net = in_skb->sk->sk_net; + struct net *net = sock_net(in_skb->sk); struct rtmsg *rtm; struct nlattr *tb[RTA_MAX+1]; struct rtable *rt = NULL; @@ -2785,7 +2785,7 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) int idx, s_idx; struct net *net; - net = skb->sk->sk_net; + net = sock_net(skb->sk); s_h = cb->args[0]; if (s_h < 0) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 28bece6f281b..46847e600a46 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1486,7 +1486,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb) if (req) return tcp_check_req(sk, skb, req, prev); - nsk = inet_lookup_established(sk->sk_net, &tcp_hashinfo, iph->saddr, + nsk = inet_lookup_established(sock_net(sk), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb)); if (nsk) { @@ -1974,7 +1974,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur) while (1) { while (req) { if (req->rsk_ops->family == st->family && - req->sk->sk_net == net) { + sock_net(req->sk) == net) { cur = req; goto out; } @@ -1998,7 +1998,7 @@ get_req: } get_sk: sk_for_each_from(sk, node) { - if (sk->sk_family == st->family && sk->sk_net == net) { + if (sk->sk_family == st->family && sock_net(sk) == net) { cur = sk; goto out; } @@ -2049,7 +2049,7 @@ static void *established_get_first(struct seq_file *seq) read_lock_bh(lock); sk_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { if (sk->sk_family != st->family || - sk->sk_net != net) { + sock_net(sk) != net) { continue; } rc = sk; @@ -2059,7 +2059,7 @@ static void *established_get_first(struct seq_file *seq) inet_twsk_for_each(tw, node, &tcp_hashinfo.ehash[st->bucket].twchain) { if (tw->tw_family != st->family || - tw->tw_net != net) { + twsk_net(tw) != net) { continue; } rc = tw; @@ -2086,7 +2086,7 @@ static void *established_get_next(struct seq_file *seq, void *cur) tw = cur; tw = tw_next(tw); get_tw: - while (tw && (tw->tw_family != st->family || tw->tw_net != net)) { + while (tw && (tw->tw_family != st->family || twsk_net(tw) != net)) { tw = tw_next(tw); } if (tw) { @@ -2107,7 +2107,7 @@ get_tw: sk = sk_next(sk); sk_for_each_from(sk, node) { - if (sk->sk_family == st->family && sk->sk_net == net) + if (sk->sk_family == st->family && sock_net(sk) == net) goto found; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index e2cd93481359..76d52d37d6ac 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -137,7 +137,7 @@ static inline int __udp_lib_lport_inuse(struct net *net, __u16 num, struct hlist_node *node; sk_for_each(sk, node, &udptable[num & (UDP_HTABLE_SIZE - 1)]) - if (sk->sk_net == net && sk->sk_hash == num) + if (sock_net(sk) == net && sk->sk_hash == num) return 1; return 0; } @@ -158,7 +158,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, struct hlist_head *head; struct sock *sk2; int error = 1; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); write_lock_bh(&udp_hash_lock); @@ -218,7 +218,7 @@ gotit: sk_for_each(sk2, node, head) if (sk2->sk_hash == snum && sk2 != sk && - sk2->sk_net == net && + sock_net(sk2) == net && (!sk2->sk_reuse || !sk->sk_reuse) && (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && @@ -269,7 +269,7 @@ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) { struct inet_sock *inet = inet_sk(sk); - if (sk->sk_net == net && sk->sk_hash == hnum && + if (sock_net(sk) == net && sk->sk_hash == hnum && !ipv6_only_sock(sk)) { int score = (sk->sk_family == PF_INET ? 1 : 0); if (inet->rcv_saddr) { @@ -607,7 +607,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, ipc.oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { - err = ip_cmsg_send(sk->sk_net, msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc); if (err) return err; if (ipc.opt) @@ -656,7 +656,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, { .sport = inet->sport, .dport = dport } } }; security_sk_classify_flow(sk, &fl); - err = ip_route_output_flow(sk->sk_net, &rt, &fl, sk, 1); + err = ip_route_output_flow(sock_net(sk), &rt, &fl, sk, 1); if (err) { if (err == -ENETUNREACH) IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); @@ -1511,7 +1511,7 @@ static struct sock *udp_get_first(struct seq_file *seq) for (state->bucket = 0; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) { struct hlist_node *node; sk_for_each(sk, node, state->hashtable + state->bucket) { - if (sk->sk_net != net) + if (sock_net(sk) != net) continue; if (sk->sk_family == state->family) goto found; @@ -1531,7 +1531,7 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) sk = sk_next(sk); try_again: ; - } while (sk && (sk->sk_net != net || sk->sk_family != state->family)); + } while (sk && (sock_net(sk) != net || sk->sk_family != state->family)); if (!sk && ++state->bucket < UDP_HTABLE_SIZE) { sk = sk_head(state->hashtable + state->bucket); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index d1de9ec74261..f2c90f145cbb 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3054,7 +3054,7 @@ static const struct nla_policy ifa_ipv6_policy[IFA_MAX+1] = { static int inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *pfx; @@ -3112,7 +3112,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, static int inet6_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *pfx; @@ -3322,7 +3322,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, struct inet6_ifaddr *ifa; struct ifmcaddr6 *ifmca; struct ifacaddr6 *ifaca; - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); s_idx = cb->args[0]; s_ip_idx = ip_idx = cb->args[1]; @@ -3418,7 +3418,7 @@ static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb) static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) { - struct net *net = in_skb->sk->sk_net; + struct net *net = sock_net(in_skb->sk); struct ifaddrmsg *ifm; struct nlattr *tb[IFA_MAX+1]; struct in6_addr *addr = NULL; @@ -3645,7 +3645,7 @@ nla_put_failure: static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); int idx, err; int s_idx = cb->args[0]; struct net_device *dev; diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index de371b5997fe..9bfa8846f262 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -364,7 +364,7 @@ static const struct nla_policy ifal_policy[IFAL_MAX+1] = { static int ip6addrlbl_newdel(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct ifaddrlblmsg *ifal; struct nlattr *tb[IFAL_MAX+1]; struct in6_addr *pfx; @@ -452,7 +452,7 @@ static int ip6addrlbl_fill(struct sk_buff *skb, static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct ip6addrlbl_entry *p; struct hlist_node *pos; int idx = 0, s_idx = cb->args[0]; @@ -490,7 +490,7 @@ static inline int ip6addrlbl_msgsize(void) static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) { - struct net *net = in_skb->sk->sk_net; + struct net *net = sock_net(in_skb->sk); struct ifaddrlblmsg *ifal; struct nlattr *tb[IFAL_MAX+1]; struct in6_addr *addr; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index f52bdaed8a1b..12f04e9d3e88 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -245,7 +245,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct sock *sk = sock->sk; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); __be32 v4addr = 0; unsigned short snum; int addr_type = 0; @@ -438,7 +438,7 @@ EXPORT_SYMBOL(inet6_getname); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); switch(cmd) { diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index e7a7fe26cebf..cac580749ebe 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -154,7 +154,7 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct nlattr **tb) { int err = -EINVAL; - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct fib6_rule *rule6 = (struct fib6_rule *) rule; if (rule->action == FR_ACT_TO_TBL) { diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 50857662e6b7..63309d10df3a 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -163,7 +163,7 @@ static inline int icmpv6_xrlim_allow(struct sock *sk, int type, struct flowi *fl) { struct dst_entry *dst; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); int res = 0; /* Informational messages are not limited. */ diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index c0c8d2d17682..21c467675412 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -105,7 +105,7 @@ struct sock *inet6_lookup_listener(struct net *net, read_lock(&hashinfo->lhash_lock); sk_for_each(sk, node, &hashinfo->listening_hash[inet_lhashfn(hnum)]) { - if (sk->sk_net == net && inet_sk(sk)->num == hnum && + if (sock_net(sk) == net && inet_sk(sk)->num == hnum && sk->sk_family == PF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); @@ -172,7 +172,7 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, struct sock *sk2; const struct hlist_node *node; struct inet_timewait_sock *tw; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); prefetch(head->chain.first); write_lock(lock); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index b0814b0082e7..b3f6e03c454c 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -346,7 +346,7 @@ end: static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); unsigned int h, s_h; unsigned int e = 0, s_e; struct rt6_rtnl_dump_arg arg; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 556300f0eba5..a8b4da25b0a7 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -910,7 +910,7 @@ static int ip6_dst_lookup_tail(struct sock *sk, struct dst_entry **dst, struct flowi *fl) { int err; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); if (*dst == NULL) *dst = ip6_route_output(net, sk, fl); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index dc6695cc5767..d3d93d752e10 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -107,7 +107,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen) { struct ipv6_pinfo *np = inet6_sk(sk); - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); int val, valbool; int retv = -ENOPROTOOPT; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 0357de8e78c8..20a3d8e2f6c6 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -181,7 +181,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, struct in6_addr *addr) struct net_device *dev = NULL; struct ipv6_mc_socklist *mc_lst; struct ipv6_pinfo *np = inet6_sk(sk); - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); int err; if (!ipv6_addr_is_multicast(addr)) @@ -255,7 +255,7 @@ int ipv6_sock_mc_drop(struct sock *sk, int ifindex, struct in6_addr *addr) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst, **lnk; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); write_lock_bh(&ipv6_sk_mc_lock); for (lnk = &np->ipv6_mc_list; (mc_lst = *lnk) !=NULL ; lnk = &mc_lst->next) { @@ -327,7 +327,7 @@ void ipv6_sock_mc_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_mc_socklist *mc_lst; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); write_lock_bh(&ipv6_sk_mc_lock); while ((mc_lst = np->ipv6_mc_list) != NULL) { @@ -365,7 +365,7 @@ int ip6_mc_source(int add, int omode, struct sock *sk, struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *psl; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); int i, j, rv; int leavegroup = 0; int pmclocked = 0; @@ -505,7 +505,7 @@ int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf) struct inet6_dev *idev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *newpsl, *psl; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); int leavegroup = 0; int i, err; @@ -598,7 +598,7 @@ int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, struct net_device *dev; struct ipv6_pinfo *inet6 = inet6_sk(sk); struct ip6_sf_socklist *psl; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); group = &((struct sockaddr_in6 *)&gsf->gf_group)->sin6_addr; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index af1ec7ba757c..70ef0d276cc0 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1879,11 +1879,11 @@ compat_do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, switch (cmd) { case IP6T_SO_SET_REPLACE: - ret = compat_do_replace(sk->sk_net, user, len); + ret = compat_do_replace(sock_net(sk), user, len); break; case IP6T_SO_SET_ADD_COUNTERS: - ret = do_add_counters(sk->sk_net, user, len, 1); + ret = do_add_counters(sock_net(sk), user, len, 1); break; default: @@ -1990,10 +1990,10 @@ compat_do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) switch (cmd) { case IP6T_SO_GET_INFO: - ret = get_info(sk->sk_net, user, len, 1); + ret = get_info(sock_net(sk), user, len, 1); break; case IP6T_SO_GET_ENTRIES: - ret = compat_get_entries(sk->sk_net, user, len); + ret = compat_get_entries(sock_net(sk), user, len); break; default: ret = do_ip6t_get_ctl(sk, cmd, user, len); @@ -2012,11 +2012,11 @@ do_ip6t_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) switch (cmd) { case IP6T_SO_SET_REPLACE: - ret = do_replace(sk->sk_net, user, len); + ret = do_replace(sock_net(sk), user, len); break; case IP6T_SO_SET_ADD_COUNTERS: - ret = do_add_counters(sk->sk_net, user, len, 0); + ret = do_add_counters(sock_net(sk), user, len, 0); break; default: @@ -2037,11 +2037,11 @@ do_ip6t_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) switch (cmd) { case IP6T_SO_GET_INFO: - ret = get_info(sk->sk_net, user, len, 0); + ret = get_info(sock_net(sk), user, len, 0); break; case IP6T_SO_GET_ENTRIES: - ret = get_entries(sk->sk_net, user, len); + ret = get_entries(sock_net(sk), user, len); break; case IP6T_SO_GET_REVISION_MATCH: diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index efb0047f6880..12c7a1560977 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -76,7 +76,7 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, if (inet_sk(sk)->num == num) { struct ipv6_pinfo *np = inet6_sk(sk); - if (sk->sk_net != net) + if (sock_net(sk) != net) continue; if (!ipv6_addr_any(&np->daddr) && @@ -280,7 +280,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (!sk->sk_bound_dev_if) goto out; - dev = dev_get_by_index(sk->sk_net, sk->sk_bound_dev_if); + dev = dev_get_by_index(sock_net(sk), sk->sk_bound_dev_if); if (!dev) { err = -ENODEV; goto out; @@ -293,7 +293,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST)) { err = -EADDRNOTAVAIL; - if (!ipv6_chk_addr(sk->sk_net, &addr->sin6_addr, + if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { if (dev) dev_put(dev); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 65053fba8c1a..ac4428371432 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2020,7 +2020,7 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid; cfg->fc_nlinfo.nlh = nlh; - cfg->fc_nlinfo.nl_net = skb->sk->sk_net; + cfg->fc_nlinfo.nl_net = sock_net(skb->sk); if (tb[RTA_GATEWAY]) { nla_memcpy(&cfg->fc_gateway, tb[RTA_GATEWAY], 16); @@ -2216,7 +2216,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg) static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) { - struct net *net = in_skb->sk->sk_net; + struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; struct rt6_info *rt; struct sk_buff *skb; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 086deffff9c9..323c7e06ef43 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1218,7 +1218,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) if (req) return tcp_check_req(sk, skb, req, prev); - nsk = __inet6_lookup_established(sk->sk_net, &tcp_hashinfo, + nsk = __inet6_lookup_established(sock_net(sk), &tcp_hashinfo, &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, ntohs(th->dest), inet6_iif(skb)); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 6683c04b427e..db266ff297e5 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -70,7 +70,7 @@ static struct sock *__udp6_lib_lookup(struct net *net, sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) { struct inet_sock *inet = inet_sk(sk); - if (sk->sk_net == net && sk->sk_hash == hnum && + if (sock_net(sk) == net && sk->sk_hash == hnum && sk->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); int score = 0; @@ -323,7 +323,7 @@ static struct sock *udp_v6_mcast_next(struct sock *sk, sk_for_each_from(s, node) { struct inet_sock *inet = inet_sk(s); - if (s->sk_net != sk->sk_net) + if (sock_net(s) != sock_net(sk)) continue; if (s->sk_hash == num && s->sk_family == PF_INET6) { diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index 6f21a53cb3e7..ae54b20d0470 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -837,7 +837,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags) IRDA_DEBUG(2, "%s()\n", __func__); - err = irda_create(sk->sk_net, newsock, sk->sk_protocol); + err = irda_create(sock_net(sk), newsock, sk->sk_protocol); if (err) return err; diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 5ebfd93ff5e7..5c6d89c6d51d 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -700,7 +700,7 @@ static struct sock *llc_create_incoming_sock(struct sock *sk, struct llc_addr *saddr, struct llc_addr *daddr) { - struct sock *newsk = llc_sk_alloc(sk->sk_net, sk->sk_family, GFP_ATOMIC, + struct sock *newsk = llc_sk_alloc(sock_net(sk), sk->sk_family, GFP_ATOMIC, sk->sk_prot); struct llc_sock *newllc, *llc = llc_sk(sk); diff --git a/net/netfilter/nf_sockopt.c b/net/netfilter/nf_sockopt.c index 3dd4b3c76d81..69d699f95f4c 100644 --- a/net/netfilter/nf_sockopt.c +++ b/net/netfilter/nf_sockopt.c @@ -65,7 +65,7 @@ static struct nf_sockopt_ops *nf_sockopt_find(struct sock *sk, int pf, { struct nf_sockopt_ops *ops; - if (sk->sk_net != &init_net) + if (sock_net(sk) != &init_net) return ERR_PTR(-ENOPROTOOPT); if (mutex_lock_interruptible(&nf_sockopt_mutex) != 0) diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 86bd8660a8f2..712a7bff8560 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -228,7 +228,7 @@ static inline struct sock *netlink_lookup(struct net *net, int protocol, read_lock(&nl_table_lock); head = nl_pid_hashfn(hash, pid); sk_for_each(sk, node, head) { - if ((sk->sk_net == net) && (nlk_sk(sk)->pid == pid)) { + if (sock_net(sk) == net && (nlk_sk(sk)->pid == pid)) { sock_hold(sk); goto found; } @@ -348,7 +348,7 @@ static int netlink_insert(struct sock *sk, struct net *net, u32 pid) head = nl_pid_hashfn(hash, pid); len = 0; sk_for_each(osk, node, head) { - if ((osk->sk_net == net) && (nlk_sk(osk)->pid == pid)) + if (sock_net(osk) == net && (nlk_sk(osk)->pid == pid)) break; len++; } @@ -486,7 +486,7 @@ static int netlink_release(struct socket *sock) if (nlk->pid && !nlk->subscriptions) { struct netlink_notify n = { - .net = sk->sk_net, + .net = sock_net(sk), .protocol = sk->sk_protocol, .pid = nlk->pid, }; @@ -518,7 +518,7 @@ static int netlink_release(struct socket *sock) static int netlink_autobind(struct socket *sock) { struct sock *sk = sock->sk; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); struct nl_pid_hash *hash = &nl_table[sk->sk_protocol].hash; struct hlist_head *head; struct sock *osk; @@ -532,7 +532,7 @@ retry: netlink_table_grab(); head = nl_pid_hashfn(hash, pid); sk_for_each(osk, node, head) { - if ((osk->sk_net != net)) + if (sock_net(osk) != net) continue; if (nlk_sk(osk)->pid == pid) { /* Bind collision, search negative pid values. */ @@ -611,7 +611,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, int addr_len) { struct sock *sk = sock->sk; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); struct netlink_sock *nlk = nlk_sk(sk); struct sockaddr_nl *nladdr = (struct sockaddr_nl *)addr; int err; @@ -720,7 +720,7 @@ static struct sock *netlink_getsockbypid(struct sock *ssk, u32 pid) struct sock *sock; struct netlink_sock *nlk; - sock = netlink_lookup(ssk->sk_net, ssk->sk_protocol, pid); + sock = netlink_lookup(sock_net(ssk), ssk->sk_protocol, pid); if (!sock) return ERR_PTR(-ECONNREFUSED); @@ -962,7 +962,7 @@ static inline int do_one_broadcast(struct sock *sk, !test_bit(p->group - 1, nlk->groups)) goto out; - if ((sk->sk_net != p->net)) + if (sock_net(sk) != p->net) goto out; if (p->failure) { @@ -1006,7 +1006,7 @@ out: int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, u32 pid, u32 group, gfp_t allocation) { - struct net *net = ssk->sk_net; + struct net *net = sock_net(ssk); struct netlink_broadcast_data info; struct hlist_node *node; struct sock *sk; @@ -1064,7 +1064,7 @@ static inline int do_one_set_err(struct sock *sk, if (sk == p->exclude_sk) goto out; - if (sk->sk_net != p->exclude_sk->sk_net) + if (sock_net(sk) != sock_net(p->exclude_sk)) goto out; if (nlk->pid == p->pid || p->group - 1 >= nlk->ngroups || @@ -1601,7 +1601,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, atomic_inc(&skb->users); cb->skb = skb; - sk = netlink_lookup(ssk->sk_net, ssk->sk_protocol, NETLINK_CB(skb).pid); + sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).pid); if (sk == NULL) { netlink_destroy_callback(cb); return -ECONNREFUSED; @@ -1643,7 +1643,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err) if (!skb) { struct sock *sk; - sk = netlink_lookup(in_skb->sk->sk_net, + sk = netlink_lookup(sock_net(in_skb->sk), in_skb->sk->sk_protocol, NETLINK_CB(in_skb).pid); if (sk) { @@ -1758,7 +1758,7 @@ static struct sock *netlink_seq_socket_idx(struct seq_file *seq, loff_t pos) for (j = 0; j <= hash->mask; j++) { sk_for_each(s, node, &hash->table[j]) { - if (iter->p.net != s->sk_net) + if (sock_net(s) != iter->p.net) continue; if (off == pos) { iter->link = i; @@ -1794,7 +1794,7 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) s = v; do { s = sk_next(s); - } while (s && (iter->p.net != s->sk_net)); + } while (s && (sock_net(s) != iter->p.net)); if (s) return s; @@ -1806,7 +1806,7 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos) for (; j <= hash->mask; j++) { s = sk_head(&hash->table[j]); - while (s && (iter->p.net != s->sk_net)) + while (s && sock_net(s) != iter->p.net) s = sk_next(s); if (s) { iter->link = i; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index a270ebf9f765..4bae8b998cab 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -466,7 +466,7 @@ static struct sock *nr_make_new(struct sock *osk) if (osk->sk_type != SOCK_SEQPACKET) return NULL; - sk = sk_alloc(osk->sk_net, PF_NETROM, GFP_ATOMIC, osk->sk_prot); + sk = sk_alloc(sock_net(osk), PF_NETROM, GFP_ATOMIC, osk->sk_prot); if (sk == NULL) return NULL; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index baa290d3444a..25070240d4ae 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -263,7 +263,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, struct if (skb->pkt_type == PACKET_LOOPBACK) goto out; - if (dev_net(dev) != sk->sk_net) + if (dev_net(dev) != sock_net(sk)) goto out; if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) @@ -337,7 +337,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock, */ saddr->spkt_device[13] = 0; - dev = dev_get_by_name(sk->sk_net, saddr->spkt_device); + dev = dev_get_by_name(sock_net(sk), saddr->spkt_device); err = -ENODEV; if (dev == NULL) goto out_unlock; @@ -451,7 +451,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet sk = pt->af_packet_priv; po = pkt_sk(sk); - if (dev_net(dev) != sk->sk_net) + if (dev_net(dev) != sock_net(sk)) goto drop; skb->dev = dev; @@ -568,7 +568,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, struct packe sk = pt->af_packet_priv; po = pkt_sk(sk); - if (dev_net(dev) != sk->sk_net) + if (dev_net(dev) != sock_net(sk)) goto drop; if (dev->header_ops) { @@ -728,7 +728,7 @@ static int packet_sendmsg(struct kiocb *iocb, struct socket *sock, } - dev = dev_get_by_index(sk->sk_net, ifindex); + dev = dev_get_by_index(sock_net(sk), ifindex); err = -ENXIO; if (dev == NULL) goto out_unlock; @@ -800,7 +800,7 @@ static int packet_release(struct socket *sock) if (!sk) return 0; - net = sk->sk_net; + net = sock_net(sk); po = pkt_sk(sk); write_lock_bh(&net->packet.sklist_lock); @@ -914,7 +914,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int add return -EINVAL; strlcpy(name,uaddr->sa_data,sizeof(name)); - dev = dev_get_by_name(sk->sk_net, name); + dev = dev_get_by_name(sock_net(sk), name); if (dev) { err = packet_do_bind(sk, dev, pkt_sk(sk)->num); dev_put(dev); @@ -941,7 +941,7 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len if (sll->sll_ifindex) { err = -ENODEV; - dev = dev_get_by_index(sk->sk_net, sll->sll_ifindex); + dev = dev_get_by_index(sock_net(sk), sll->sll_ifindex); if (dev == NULL) goto out; } @@ -1135,7 +1135,7 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; - dev = dev_get_by_index(sk->sk_net, pkt_sk(sk)->ifindex); + dev = dev_get_by_index(sock_net(sk), pkt_sk(sk)->ifindex); if (dev) { strlcpy(uaddr->sa_data, dev->name, 15); dev_put(dev); @@ -1160,7 +1160,7 @@ static int packet_getname(struct socket *sock, struct sockaddr *uaddr, sll->sll_family = AF_PACKET; sll->sll_ifindex = po->ifindex; sll->sll_protocol = po->num; - dev = dev_get_by_index(sk->sk_net, po->ifindex); + dev = dev_get_by_index(sock_net(sk), po->ifindex); if (dev) { sll->sll_hatype = dev->type; sll->sll_halen = dev->addr_len; @@ -1212,7 +1212,7 @@ static int packet_mc_add(struct sock *sk, struct packet_mreq_max *mreq) rtnl_lock(); err = -ENODEV; - dev = __dev_get_by_index(sk->sk_net, mreq->mr_ifindex); + dev = __dev_get_by_index(sock_net(sk), mreq->mr_ifindex); if (!dev) goto done; @@ -1266,7 +1266,7 @@ static int packet_mc_drop(struct sock *sk, struct packet_mreq_max *mreq) if (--ml->count == 0) { struct net_device *dev; *mlp = ml->next; - dev = dev_get_by_index(sk->sk_net, ml->ifindex); + dev = dev_get_by_index(sock_net(sk), ml->ifindex); if (dev) { packet_dev_mc(dev, ml, -1); dev_put(dev); @@ -1294,7 +1294,7 @@ static void packet_flush_mclist(struct sock *sk) struct net_device *dev; po->mclist = ml->next; - if ((dev = dev_get_by_index(sk->sk_net, ml->ifindex)) != NULL) { + if ((dev = dev_get_by_index(sock_net(sk), ml->ifindex)) != NULL) { packet_dev_mc(dev, ml, -1); dev_put(dev); } @@ -1540,7 +1540,7 @@ static int packet_ioctl(struct socket *sock, unsigned int cmd, case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCSIFFLAGS: - if (sk->sk_net != &init_net) + if (sock_net(sk) != &init_net) return -ENOIOCTLCMD; return inet_dgram_ops.ioctl(sock, cmd, arg); #endif diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 1a7f143cf741..92d85c38e4d2 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -551,7 +551,7 @@ static struct sock *rose_make_new(struct sock *osk) if (osk->sk_type != SOCK_SEQPACKET) return NULL; - sk = sk_alloc(osk->sk_net, PF_ROSE, GFP_ATOMIC, &rose_proto); + sk = sk_alloc(sock_net(osk), PF_ROSE, GFP_ATOMIC, &rose_proto); if (sk == NULL) return NULL; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 0b8eb235bc13..74e662cbb2c5 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -951,7 +951,7 @@ done: static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_ACT_MAX + 1]; u32 pid = skb ? NETLINK_CB(skb).pid : 0; int ret = 0, ovr = 0; @@ -1029,7 +1029,7 @@ find_dump_kind(struct nlmsghdr *n) static int tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 0fbedcabf111..1086df7478bc 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -118,7 +118,7 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; struct tcmsg *t; u32 protocol; @@ -389,7 +389,7 @@ static int tcf_node_dump(struct tcf_proto *tp, unsigned long n, static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); int t; int s_t; struct net_device *dev; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 7e3c048ba9b1..15b91a9ee8e8 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -605,7 +605,7 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w) static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct tcmsg *tcm = NLMSG_DATA(n); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; @@ -674,7 +674,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct tcmsg *tcm; struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; @@ -893,7 +893,7 @@ err_out: static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); int idx, q_idx; int s_idx, s_q_idx; struct net_device *dev; @@ -945,7 +945,7 @@ done: static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); struct tcmsg *tcm = NLMSG_DATA(n); struct nlattr *tca[TCA_MAX + 1]; struct net_device *dev; @@ -1139,7 +1139,7 @@ static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, struct qdisc_walk static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) { - struct net *net = skb->sk->sk_net; + struct net *net = sock_net(skb->sk); int t; int s_t; struct net_device *dev; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index dc71d0d83753..036bfcc8d15b 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -636,7 +636,7 @@ static struct sock *sctp_v6_create_accept_sk(struct sock *sk, struct ipv6_pinfo *newnp, *np = inet6_sk(sk); struct sctp6_sock *newsctp6sk; - newsk = sk_alloc(sk->sk_net, PF_INET6, GFP_KERNEL, sk->sk_prot); + newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot); if (!newsk) goto out; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 2faa0d8839eb..5aea91137fbb 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -554,7 +554,7 @@ static struct sock *sctp_v4_create_accept_sk(struct sock *sk, { struct inet_sock *inet = inet_sk(sk); struct inet_sock *newinet; - struct sock *newsk = sk_alloc(sk->sk_net, PF_INET, GFP_KERNEL, + struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL, sk->sk_prot); if (!newsk) diff --git a/net/socket.c b/net/socket.c index 9d3fbfbc8535..79e5382fd110 100644 --- a/net/socket.c +++ b/net/socket.c @@ -857,7 +857,7 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) sock = file->private_data; sk = sock->sk; - net = sk->sk_net; + net = sock_net(sk); if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) { err = dev_ioctl(net, cmd, argp); } else @@ -1375,7 +1375,7 @@ asmlinkage long sys_listen(int fd, int backlog) sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { - somaxconn = sock->sk->sk_net->sysctl_somaxconn; + somaxconn = sock_net(sock->sk)->sysctl_somaxconn; if ((unsigned)backlog > somaxconn) backlog = somaxconn; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 3220d5cb5b5d..ae45df060e3a 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1375,7 +1375,7 @@ static int accept(struct socket *sock, struct socket *newsock, int flags) } buf = skb_peek(&sock->sk->sk_receive_queue); - res = tipc_create(sock->sk->sk_net, newsock, 0); + res = tipc_create(sock_net(sock->sk), newsock, 0); if (!res) { struct tipc_sock *new_tsock = tipc_sk(newsock->sk); struct tipc_portid id; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index ae584356852c..cb9d0cb5f270 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -252,7 +252,7 @@ static struct sock *__unix_find_socket_byname(struct net *net, sk_for_each(s, node, &unix_socket_table[hash ^ type]) { struct unix_sock *u = unix_sk(s); - if (s->sk_net != net) + if (sock_net(s) != net) continue; if (u->addr->len == len && @@ -289,7 +289,7 @@ static struct sock *unix_find_socket_byinode(struct net *net, struct inode *i) &unix_socket_table[i->i_ino & (UNIX_HASH_SIZE - 1)]) { struct dentry *dentry = unix_sk(s)->dentry; - if (s->sk_net != net) + if (sock_net(s) != net) continue; if(dentry && dentry->d_inode == i) @@ -654,7 +654,7 @@ static int unix_release(struct socket *sock) static int unix_autobind(struct socket *sock) { struct sock *sk = sock->sk; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); struct unix_sock *u = unix_sk(sk); static u32 ordernum = 1; struct unix_address * addr; @@ -758,7 +758,7 @@ fail: static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr=(struct sockaddr_un *)uaddr; struct dentry * dentry = NULL; @@ -899,7 +899,7 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { struct sock *sk = sock->sk; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); struct sockaddr_un *sunaddr=(struct sockaddr_un*)addr; struct sock *other; unsigned hash; @@ -996,7 +996,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, { struct sockaddr_un *sunaddr=(struct sockaddr_un *)uaddr; struct sock *sk = sock->sk; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); struct unix_sock *u = unix_sk(sk), *newu, *otheru; struct sock *newsk = NULL; struct sock *other = NULL; @@ -1025,7 +1025,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, err = -ENOMEM; /* create new sock for complete connection */ - newsk = unix_create1(sk->sk_net, NULL); + newsk = unix_create1(sock_net(sk), NULL); if (newsk == NULL) goto out; @@ -1312,7 +1312,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, { struct sock_iocb *siocb = kiocb_to_siocb(kiocb); struct sock *sk = sock->sk; - struct net *net = sk->sk_net; + struct net *net = sock_net(sk); struct unix_sock *u = unix_sk(sk); struct sockaddr_un *sunaddr=msg->msg_name; struct sock *other = NULL; @@ -2022,7 +2022,7 @@ static struct sock *unix_seq_idx(struct unix_iter_state *iter, loff_t pos) struct sock *s; for (s = first_unix_socket(&iter->i); s; s = next_unix_socket(&iter->i, s)) { - if (s->sk_net != iter->p.net) + if (sock_net(s) != iter->p.net) continue; if (off == pos) return s; @@ -2050,7 +2050,7 @@ static void *unix_seq_next(struct seq_file *seq, void *v, loff_t *pos) sk = first_unix_socket(&iter->i); else sk = next_unix_socket(&iter->i, sk); - while (sk && (sk->sk_net != iter->p.net)) + while (sk && (sock_net(sk) != iter->p.net)) sk = next_unix_socket(&iter->i, sk); return sk; } diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 7a46ea73fe2d..6ba67c523c16 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -549,7 +549,7 @@ static struct sock *x25_make_new(struct sock *osk) if (osk->sk_type != SOCK_SEQPACKET) goto out; - if ((sk = x25_alloc_socket(osk->sk_net)) == NULL) + if ((sk = x25_alloc_socket(sock_net(osk))) == NULL) goto out; x25 = x25_sk(sk); -- cgit v1.2.3 From 7bc570c8b4f75ddb3fd5dbeb38127cdc4acbcc9c Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Thu, 3 Apr 2008 09:22:53 +0900 Subject: [IPV6] MROUTE: Support multicast forwarding. Based on ancient patch by Mickael Hoerdt , which is available at . Signed-off-by: YOSHIFUJI Hideaki --- include/linux/Kbuild | 1 + include/linux/ipv6.h | 5 + include/linux/mroute6.h | 227 ++++++++ net/ipv6/Kconfig | 7 + net/ipv6/Makefile | 2 + net/ipv6/addrconf.c | 15 +- net/ipv6/af_inet6.c | 6 + net/ipv6/ip6_input.c | 87 ++- net/ipv6/ip6_output.c | 6 +- net/ipv6/ip6mr.c | 1384 ++++++++++++++++++++++++++++++++++++++++++++++ net/ipv6/ipv6_sockglue.c | 7 + net/ipv6/raw.c | 7 +- net/ipv6/route.c | 30 +- 13 files changed, 1754 insertions(+), 30 deletions(-) create mode 100644 include/linux/mroute6.h create mode 100644 net/ipv6/ip6mr.c (limited to 'include/linux/ipv6.h') diff --git a/include/linux/Kbuild b/include/linux/Kbuild index 84736acb4b99..29ab9b95d376 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -261,6 +261,7 @@ unifdef-y += mempolicy.h unifdef-y += mii.h unifdef-y += mman.h unifdef-y += mroute.h +unifdef-y += mroute6.h unifdef-y += msdos_fs.h unifdef-y += msg.h unifdef-y += nbd.h diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index b90d3d461d4e..f53e4764fc05 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -159,6 +159,9 @@ struct ipv6_devconf { __s32 accept_source_route; #ifdef CONFIG_IPV6_OPTIMISTIC_DAD __s32 optimistic_dad; +#endif +#ifdef CONFIG_IPV6_MROUTE + __s32 mc_forwarding; #endif void *sysctl; }; @@ -190,6 +193,7 @@ enum { DEVCONF_PROXY_NDP, DEVCONF_OPTIMISTIC_DAD, DEVCONF_ACCEPT_SOURCE_ROUTE, + DEVCONF_MC_FORWARDING, DEVCONF_MAX }; @@ -230,6 +234,7 @@ struct inet6_skb_parm { #endif #define IP6SKB_XFRM_TRANSFORMED 1 +#define IP6SKB_FORWARDED 2 }; #define IP6CB(skb) ((struct inet6_skb_parm*)((skb)->cb)) diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h new file mode 100644 index 000000000000..b92190304e0b --- /dev/null +++ b/include/linux/mroute6.h @@ -0,0 +1,227 @@ +#ifndef __LINUX_MROUTE6_H +#define __LINUX_MROUTE6_H + +#include +#include + +/* + * Based on the MROUTING 3.5 defines primarily to keep + * source compatibility with BSD. + * + * See the pim6sd code for the original history. + * + * Protocol Independent Multicast (PIM) data structures included + * Carlos Picoto (cap@di.fc.ul.pt) + * + */ + +#define MRT6_BASE 200 +#define MRT6_INIT (MRT6_BASE) /* Activate the kernel mroute code */ +#define MRT6_DONE (MRT6_BASE+1) /* Shutdown the kernel mroute */ +#define MRT6_ADD_MIF (MRT6_BASE+2) /* Add a virtual interface */ +#define MRT6_DEL_MIF (MRT6_BASE+3) /* Delete a virtual interface */ +#define MRT6_ADD_MFC (MRT6_BASE+4) /* Add a multicast forwarding entry */ +#define MRT6_DEL_MFC (MRT6_BASE+5) /* Delete a multicast forwarding entry */ +#define MRT6_VERSION (MRT6_BASE+6) /* Get the kernel multicast version */ + +#define SIOCGETMIFCNT_IN6 SIOCPROTOPRIVATE /* IP protocol privates */ +#define SIOCGETSGCNT_IN6 (SIOCPROTOPRIVATE+1) +#define SIOCGETRPF (SIOCPROTOPRIVATE+2) + +#define MAXMIFS 32 +typedef unsigned long mifbitmap_t; /* User mode code depends on this lot */ +typedef unsigned short mifi_t; +#define ALL_MIFS ((mifi_t)(-1)) + +#ifndef IF_SETSIZE +#define IF_SETSIZE 256 +#endif + +typedef __u32 if_mask; +#define NIFBITS (sizeof(if_mask) * 8) /* bits per mask */ + +#if !defined(__KERNEL__) && !defined(DIV_ROUND_UP) +#define DIV_ROUND_UP(x,y) (((x) + ((y) - 1)) / (y)) +#endif + +typedef struct if_set { + if_mask ifs_bits[DIV_ROUND_UP(IF_SETSIZE, NIFBITS)]; +} if_set; + +#define IF_SET(n, p) ((p)->ifs_bits[(n)/NIFBITS] |= (1 << ((n) % NIFBITS))) +#define IF_CLR(n, p) ((p)->ifs_bits[(n)/NIFBITS] &= ~(1 << ((n) % NIFBITS))) +#define IF_ISSET(n, p) ((p)->ifs_bits[(n)/NIFBITS] & (1 << ((n) % NIFBITS))) +#define IF_COPY(f, t) bcopy(f, t, sizeof(*(f))) +#define IF_ZERO(p) bzero(p, sizeof(*(p))) + +/* + * Passed by mrouted for an MRT_ADD_MIF - again we use the + * mrouted 3.6 structures for compatibility + */ + +struct mif6ctl { + mifi_t mif6c_mifi; /* Index of MIF */ + unsigned char mif6c_flags; /* MIFF_ flags */ + unsigned char vifc_threshold; /* ttl limit */ + u_short mif6c_pifi; /* the index of the physical IF */ + unsigned int vifc_rate_limit; /* Rate limiter values (NI) */ +}; + +#define MIFF_REGISTER 0x1 /* register vif */ + +/* + * Cache manipulation structures for mrouted and PIMd + */ + +struct mf6cctl +{ + struct sockaddr_in6 mf6cc_origin; /* Origin of mcast */ + struct sockaddr_in6 mf6cc_mcastgrp; /* Group in question */ + mifi_t mf6cc_parent; /* Where it arrived */ + struct if_set mf6cc_ifset; /* Where it is going */ +}; + +/* + * Group count retrieval for pim6sd + */ + +struct sioc_sg_req6 +{ + struct sockaddr_in6 src; + struct sockaddr_in6 grp; + unsigned long pktcnt; + unsigned long bytecnt; + unsigned long wrong_if; +}; + +/* + * To get vif packet counts + */ + +struct sioc_mif_req6 +{ + mifi_t mifi; /* Which iface */ + unsigned long icount; /* In packets */ + unsigned long ocount; /* Out packets */ + unsigned long ibytes; /* In bytes */ + unsigned long obytes; /* Out bytes */ +}; + +/* + * That's all usermode folks + */ + +#ifdef __KERNEL__ + +#include /* for struct sk_buff_head */ + +struct net_device; +struct inet6_dev *ipv6_find_idev(struct net_device *dev); + +#ifdef CONFIG_IPV6_MROUTE +static inline int ip6_mroute_opt(int opt) +{ + return (opt >= MRT6_BASE) && (opt <= MRT6_BASE + 10); +} +#else +static inline int ip6_mroute_opt(int opt) +{ + return 0; +} +#endif + +struct sock; + +extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, int); +extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *); +extern int ip6_mr_input(struct sk_buff *skb); +extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg); +extern void ip6_mr_init(void); + +struct mif_device +{ + struct net_device *dev; /* Device we are using */ + unsigned long bytes_in,bytes_out; + unsigned long pkt_in,pkt_out; /* Statistics */ + unsigned long rate_limit; /* Traffic shaping (NI) */ + unsigned char threshold; /* TTL threshold */ + unsigned short flags; /* Control flags */ + int link; /* Physical interface index */ +}; + +#define VIFF_STATIC 0x8000 + +struct mfc6_cache +{ + struct mfc6_cache *next; /* Next entry on cache line */ + struct in6_addr mf6c_mcastgrp; /* Group the entry belongs to */ + struct in6_addr mf6c_origin; /* Source of packet */ + mifi_t mf6c_parent; /* Source interface */ + int mfc_flags; /* Flags on line */ + + union { + struct { + unsigned long expires; + struct sk_buff_head unresolved; /* Unresolved buffers */ + } unres; + struct { + unsigned long last_assert; + int minvif; + int maxvif; + unsigned long bytes; + unsigned long pkt; + unsigned long wrong_if; + unsigned char ttls[MAXMIFS]; /* TTL thresholds */ + } res; + } mfc_un; +}; + +#define MFC_STATIC 1 +#define MFC_NOTIFY 2 + +#define MFC6_LINES 64 + +#define MFC6_HASH(a, g) (((__force u32)(a)->s6_addr32[0] ^ \ + (__force u32)(a)->s6_addr32[1] ^ \ + (__force u32)(a)->s6_addr32[2] ^ \ + (__force u32)(a)->s6_addr32[3] ^ \ + (__force u32)(g)->s6_addr32[0] ^ \ + (__force u32)(g)->s6_addr32[1] ^ \ + (__force u32)(g)->s6_addr32[2] ^ \ + (__force u32)(g)->s6_addr32[3]) % MFC6_LINES) + +#define MFC_ASSERT_THRESH (3*HZ) /* Maximal freq. of asserts */ + +#endif + +#ifdef __KERNEL__ +struct rtmsg; +extern int ip6mr_get_route(struct sk_buff *skb, struct rtmsg *rtm, int nowait); + +#ifdef CONFIG_IPV6_MROUTE +extern struct sock *mroute6_socket; +extern int ip6mr_sk_done(struct sock *sk); +#else +#define mroute6_socket NULL +static inline int ip6mr_sk_done(struct sock *sk) { return 0; } +#endif +#endif + +/* + * Structure used to communicate from kernel to multicast router. + * We'll overlay the structure onto an MLD header (not an IPv6 heder like igmpmsg{} + * used for IPv4 implementation). This is because this structure will be passed via an + * IPv6 raw socket, on wich an application will only receiver the payload i.e the data after + * the IPv6 header and all the extension headers. (See section 3 of RFC 3542) + */ + +struct mrt6msg { +#define MRT6MSG_NOCACHE 1 + __u8 im6_mbz; /* must be zero */ + __u8 im6_msgtype; /* what type of message */ + __u16 im6_mif; /* mif rec'd on */ + __u32 im6_pad; /* padding for 64 bit arch */ + struct in6_addr im6_src, im6_dst; +}; + +#endif diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 47263e45bacb..9a2ea81e499f 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -209,3 +209,10 @@ config IPV6_SUBTREES If unsure, say N. +config IPV6_MROUTE + bool "IPv6: multicast routing (EXPERIMENTAL)" + depends on IPV6 && EXPERIMENTAL + ---help--- + Experimental support for IPv6 multicast forwarding. + If unsure, say N. + diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index ae14617e607f..686934acfac1 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -11,6 +11,8 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o \ exthdrs.o datagram.o ip6_flowlabel.o inet6_connection_sock.o ipv6-$(CONFIG_SYSCTL) = sysctl_net_ipv6.o +ipv6-$(CONFIG_IPV6_MROUTE) += ip6mr.o + ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \ xfrm6_output.o ipv6-$(CONFIG_NETFILTER) += netfilter.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 11037615bc73..dbc51af69017 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -412,7 +412,7 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) return ndev; } -static struct inet6_dev * ipv6_find_idev(struct net_device *dev) +struct inet6_dev * ipv6_find_idev(struct net_device *dev) { struct inet6_dev *idev; @@ -3547,6 +3547,9 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, #ifdef CONFIG_IPV6_OPTIMISTIC_DAD array[DEVCONF_OPTIMISTIC_DAD] = cnf->optimistic_dad; #endif +#ifdef CONFIG_IPV6_MROUTE + array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding; +#endif } static inline size_t inet6_if_nlmsg_size(void) @@ -4094,6 +4097,16 @@ static struct addrconf_sysctl_table .proc_handler = &proc_dointvec, }, +#endif +#ifdef CONFIG_IPV6_MROUTE + { + .ctl_name = CTL_UNNUMBERED, + .procname = "mc_forwarding", + .data = &ipv6_devconf.mc_forwarding, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, #endif { .ctl_name = 0, /* sentinel */ diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 1731b0abf7f5..3c6aafb02183 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -61,6 +61,9 @@ #include #include +#ifdef CONFIG_IPV6_MROUTE +#include +#endif MODULE_AUTHOR("Cast of dozens"); MODULE_DESCRIPTION("IPv6 protocol stack for Linux"); @@ -953,6 +956,9 @@ static int __init inet6_init(void) err = icmpv6_init(); if (err) goto icmp_fail; +#ifdef CONFIG_IPV6_MROUTE + ip6_mr_init(); +#endif err = ndisc_init(); if (err) goto ndisc_fail; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 43a617e2268b..09a3201e408a 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -29,6 +29,7 @@ #include #include #include +#include #include #include @@ -236,36 +237,84 @@ int ip6_mc_input(struct sk_buff *skb) hdr = ipv6_hdr(skb); deliver = ipv6_chk_mcast_addr(skb->dev, &hdr->daddr, NULL); +#ifdef CONFIG_IPV6_MROUTE /* - * IPv6 multicast router mode isnt currently supported. + * IPv6 multicast router mode is now supported ;) */ -#if 0 - if (ipv6_config.multicast_route) { - int addr_type; - - addr_type = ipv6_addr_type(&hdr->daddr); - - if (!(addr_type & (IPV6_ADDR_LOOPBACK | IPV6_ADDR_LINKLOCAL))) { - struct sk_buff *skb2; - struct dst_entry *dst; + if (ipv6_devconf.mc_forwarding && + likely(!(IP6CB(skb)->flags & IP6SKB_FORWARDED))) { + /* + * Okay, we try to forward - split and duplicate + * packets. + */ + struct sk_buff *skb2; + struct inet6_skb_parm *opt = IP6CB(skb); + + /* Check for MLD */ + if (unlikely(opt->ra)) { + /* Check if this is a mld message */ + u8 *ptr = skb_network_header(skb) + opt->ra; + struct icmp6hdr *icmp6; + u8 nexthdr = hdr->nexthdr; + int offset; + + /* Check if the value of Router Alert + * is for MLD (0x0000). + */ + if ((ptr[2] | ptr[3]) == 0) { + if (!ipv6_ext_hdr(nexthdr)) { + /* BUG */ + goto discard; + } + offset = ipv6_skip_exthdr(skb, sizeof(*hdr), + &nexthdr); + if (offset < 0) + goto discard; + + if (nexthdr != IPPROTO_ICMPV6) + goto discard; + + if (!pskb_may_pull(skb, (skb_network_header(skb) + + offset + 1 - skb->data))) + goto discard; + + icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset); + + switch (icmp6->icmp6_type) { + case ICMPV6_MGM_QUERY: + case ICMPV6_MGM_REPORT: + case ICMPV6_MGM_REDUCTION: + case ICMPV6_MLD2_REPORT: + break; + default: + /* Bogus */ + goto discard; + } + deliver = 1; + goto out; + } + /* unknown RA - process it normally */ + } - dst = skb->dst; + if (deliver) + skb2 = skb_clone(skb, GFP_ATOMIC); + else { + skb2 = skb; + skb = NULL; + } - if (deliver) { - skb2 = skb_clone(skb, GFP_ATOMIC); - dst_output(skb2); - } else { - dst_output(skb); - return 0; - } + if (skb2) { + skb2->dev = skb2->dst->dev; + ip6_mr_input(skb2); } } #endif - +out: if (likely(deliver)) { ip6_input(skb); return 0; } +discard: /* discard */ kfree_skb(skb); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a8b4da25b0a7..c0dbe549cc42 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -55,6 +55,7 @@ #include #include #include +#include static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)); @@ -137,8 +138,9 @@ static int ip6_output2(struct sk_buff *skb) struct inet6_dev *idev = ip6_dst_idev(skb->dst); if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) && - ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, - &ipv6_hdr(skb)->saddr)) { + ((mroute6_socket && !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) || + ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr, + &ipv6_hdr(skb)->saddr))) { struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); /* Do not check for IFF_ALLMULTI; multicast routing diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c new file mode 100644 index 000000000000..1bdf3c177d58 --- /dev/null +++ b/net/ipv6/ip6mr.c @@ -0,0 +1,1384 @@ +/* + * Linux IPv6 multicast routing support for BSD pim6sd + * Based on net/ipv4/ipmr.c. + * + * (c) 2004 Mickael Hoerdt, + * LSIIT Laboratory, Strasbourg, France + * (c) 2004 Jean-Philippe Andriot, + * 6WIND, Paris, France + * Copyright (C)2007,2008 USAGI/WIDE Project + * YOSHIFUJI Hideaki + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +struct sock *mroute6_socket; + + +/* Big lock, protecting vif table, mrt cache and mroute socket state. + Note that the changes are semaphored via rtnl_lock. + */ + +static DEFINE_RWLOCK(mrt_lock); + +/* + * Multicast router control variables + */ + +static struct mif_device vif6_table[MAXMIFS]; /* Devices */ +static int maxvif; + +#define MIF_EXISTS(idx) (vif6_table[idx].dev != NULL) + +static struct mfc6_cache *mfc6_cache_array[MFC_LINES]; /* Forwarding cache */ + +static struct mfc6_cache *mfc_unres_queue; /* Queue of unresolved entries */ +static atomic_t cache_resolve_queue_len; /* Size of unresolved */ + +/* Special spinlock for queue of unresolved entries */ +static DEFINE_SPINLOCK(mfc_unres_lock); + +/* We return to original Alan's scheme. Hash table of resolved + entries is changed only in process context and protected + with weak lock mrt_lock. Queue of unresolved entries is protected + with strong spinlock mfc_unres_lock. + + In this case data path is free of exclusive locks at all. + */ + +static struct kmem_cache *mrt_cachep __read_mostly; + +static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache); +static int ip6mr_cache_report(struct sk_buff *pkt, vifi_t vifi, int assert); +static int ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm); + +static struct timer_list ipmr_expire_timer; + + +#ifdef CONFIG_PROC_FS + +struct ipmr_mfc_iter { + struct mfc6_cache **cache; + int ct; +}; + + +static struct mfc6_cache *ipmr_mfc_seq_idx(struct ipmr_mfc_iter *it, loff_t pos) +{ + struct mfc6_cache *mfc; + + it->cache = mfc6_cache_array; + read_lock(&mrt_lock); + for (it->ct = 0; it->ct < ARRAY_SIZE(mfc6_cache_array); it->ct++) + for (mfc = mfc6_cache_array[it->ct]; mfc; mfc = mfc->next) + if (pos-- == 0) + return mfc; + read_unlock(&mrt_lock); + + it->cache = &mfc_unres_queue; + spin_lock_bh(&mfc_unres_lock); + for (mfc = mfc_unres_queue; mfc; mfc = mfc->next) + if (pos-- == 0) + return mfc; + spin_unlock_bh(&mfc_unres_lock); + + it->cache = NULL; + return NULL; +} + + + + +/* + * The /proc interfaces to multicast routing /proc/ip6_mr_cache /proc/ip6_mr_vif + */ + +struct ipmr_vif_iter { + int ct; +}; + +static struct mif_device *ip6mr_vif_seq_idx(struct ipmr_vif_iter *iter, + loff_t pos) +{ + for (iter->ct = 0; iter->ct < maxvif; ++iter->ct) { + if (!MIF_EXISTS(iter->ct)) + continue; + if (pos-- == 0) + return &vif6_table[iter->ct]; + } + return NULL; +} + +static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos) + __acquires(mrt_lock) +{ + read_lock(&mrt_lock); + return (*pos ? ip6mr_vif_seq_idx(seq->private, *pos - 1) + : SEQ_START_TOKEN); +} + +static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct ipmr_vif_iter *iter = seq->private; + + ++*pos; + if (v == SEQ_START_TOKEN) + return ip6mr_vif_seq_idx(iter, 0); + + while (++iter->ct < maxvif) { + if (!MIF_EXISTS(iter->ct)) + continue; + return &vif6_table[iter->ct]; + } + return NULL; +} + +static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v) + __releases(mrt_lock) +{ + read_unlock(&mrt_lock); +} + +static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) +{ + if (v == SEQ_START_TOKEN) { + seq_puts(seq, + "Interface BytesIn PktsIn BytesOut PktsOut Flags\n"); + } else { + const struct mif_device *vif = v; + const char *name = vif->dev ? vif->dev->name : "none"; + + seq_printf(seq, + "%2Zd %-10s %8ld %7ld %8ld %7ld %05X\n", + vif - vif6_table, + name, vif->bytes_in, vif->pkt_in, + vif->bytes_out, vif->pkt_out, + vif->flags); + } + return 0; +} + +static struct seq_operations ip6mr_vif_seq_ops = { + .start = ip6mr_vif_seq_start, + .next = ip6mr_vif_seq_next, + .stop = ip6mr_vif_seq_stop, + .show = ip6mr_vif_seq_show, +}; + +static int ip6mr_vif_open(struct inode *inode, struct file *file) +{ + return seq_open_private(file, &ip6mr_vif_seq_ops, + sizeof(struct ipmr_vif_iter)); +} + +static struct file_operations ip6mr_vif_fops = { + .owner = THIS_MODULE, + .open = ip6mr_vif_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos) +{ + return (*pos ? ipmr_mfc_seq_idx(seq->private, *pos - 1) + : SEQ_START_TOKEN); +} + +static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct mfc6_cache *mfc = v; + struct ipmr_mfc_iter *it = seq->private; + + ++*pos; + + if (v == SEQ_START_TOKEN) + return ipmr_mfc_seq_idx(seq->private, 0); + + if (mfc->next) + return mfc->next; + + if (it->cache == &mfc_unres_queue) + goto end_of_list; + + BUG_ON(it->cache != mfc6_cache_array); + + while (++it->ct < ARRAY_SIZE(mfc6_cache_array)) { + mfc = mfc6_cache_array[it->ct]; + if (mfc) + return mfc; + } + + /* exhausted cache_array, show unresolved */ + read_unlock(&mrt_lock); + it->cache = &mfc_unres_queue; + it->ct = 0; + + spin_lock_bh(&mfc_unres_lock); + mfc = mfc_unres_queue; + if (mfc) + return mfc; + + end_of_list: + spin_unlock_bh(&mfc_unres_lock); + it->cache = NULL; + + return NULL; +} + +static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) +{ + struct ipmr_mfc_iter *it = seq->private; + + if (it->cache == &mfc_unres_queue) + spin_unlock_bh(&mfc_unres_lock); + else if (it->cache == mfc6_cache_array) + read_unlock(&mrt_lock); +} + +static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) +{ + int n; + + if (v == SEQ_START_TOKEN) { + seq_puts(seq, + "Group " + "Origin " + "Iif Pkts Bytes Wrong Oifs\n"); + } else { + const struct mfc6_cache *mfc = v; + const struct ipmr_mfc_iter *it = seq->private; + + seq_printf(seq, + NIP6_FMT " " NIP6_FMT " %-3d %8ld %8ld %8ld", + NIP6(mfc->mf6c_mcastgrp), NIP6(mfc->mf6c_origin), + mfc->mf6c_parent, + mfc->mfc_un.res.pkt, + mfc->mfc_un.res.bytes, + mfc->mfc_un.res.wrong_if); + + if (it->cache != &mfc_unres_queue) { + for (n = mfc->mfc_un.res.minvif; + n < mfc->mfc_un.res.maxvif; n++) { + if (MIF_EXISTS(n) && + mfc->mfc_un.res.ttls[n] < 255) + seq_printf(seq, + " %2d:%-3d", + n, mfc->mfc_un.res.ttls[n]); + } + } + seq_putc(seq, '\n'); + } + return 0; +} + +static struct seq_operations ipmr_mfc_seq_ops = { + .start = ipmr_mfc_seq_start, + .next = ipmr_mfc_seq_next, + .stop = ipmr_mfc_seq_stop, + .show = ipmr_mfc_seq_show, +}; + +static int ipmr_mfc_open(struct inode *inode, struct file *file) +{ + return seq_open_private(file, &ipmr_mfc_seq_ops, + sizeof(struct ipmr_mfc_iter)); +} + +static struct file_operations ip6mr_mfc_fops = { + .owner = THIS_MODULE, + .open = ipmr_mfc_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; +#endif + +/* + * Delete a VIF entry + */ + +static int mif6_delete(int vifi) +{ + struct mif_device *v; + struct net_device *dev; + if (vifi < 0 || vifi >= maxvif) + return -EADDRNOTAVAIL; + + v = &vif6_table[vifi]; + + write_lock_bh(&mrt_lock); + dev = v->dev; + v->dev = NULL; + + if (!dev) { + write_unlock_bh(&mrt_lock); + return -EADDRNOTAVAIL; + } + + if (vifi + 1 == maxvif) { + int tmp; + for (tmp = vifi - 1; tmp >= 0; tmp--) { + if (MIF_EXISTS(tmp)) + break; + } + maxvif = tmp + 1; + } + + write_unlock_bh(&mrt_lock); + + dev_set_allmulti(dev, -1); + + if (v->flags & MIFF_REGISTER) + unregister_netdevice(dev); + + dev_put(dev); + return 0; +} + +/* Destroy an unresolved cache entry, killing queued skbs + and reporting error to netlink readers. + */ + +static void ip6mr_destroy_unres(struct mfc6_cache *c) +{ + struct sk_buff *skb; + + atomic_dec(&cache_resolve_queue_len); + + while((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) { + if (ipv6_hdr(skb)->version == 0) { + struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr)); + nlh->nlmsg_type = NLMSG_ERROR; + nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr)); + skb_trim(skb, nlh->nlmsg_len); + ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -ETIMEDOUT; + rtnl_unicast(skb, &init_net, NETLINK_CB(skb).pid); + } else + kfree_skb(skb); + } + + kmem_cache_free(mrt_cachep, c); +} + + +/* Single timer process for all the unresolved queue. */ + +static void ipmr_do_expire_process(unsigned long dummy) +{ + unsigned long now = jiffies; + unsigned long expires = 10 * HZ; + struct mfc6_cache *c, **cp; + + cp = &mfc_unres_queue; + + while ((c = *cp) != NULL) { + if (time_after(c->mfc_un.unres.expires, now)) { + /* not yet... */ + unsigned long interval = c->mfc_un.unres.expires - now; + if (interval < expires) + expires = interval; + cp = &c->next; + continue; + } + + *cp = c->next; + ip6mr_destroy_unres(c); + } + + if (atomic_read(&cache_resolve_queue_len)) + mod_timer(&ipmr_expire_timer, jiffies + expires); +} + +static void ipmr_expire_process(unsigned long dummy) +{ + if (!spin_trylock(&mfc_unres_lock)) { + mod_timer(&ipmr_expire_timer, jiffies + 1); + return; + } + + if (atomic_read(&cache_resolve_queue_len)) + ipmr_do_expire_process(dummy); + + spin_unlock(&mfc_unres_lock); +} + +/* Fill oifs list. It is called under write locked mrt_lock. */ + +static void ip6mr_update_thresholds(struct mfc6_cache *cache, unsigned char *ttls) +{ + int vifi; + + cache->mfc_un.res.minvif = MAXVIFS; + cache->mfc_un.res.maxvif = 0; + memset(cache->mfc_un.res.ttls, 255, MAXVIFS); + + for (vifi = 0; vifi < maxvif; vifi++) { + if (MIF_EXISTS(vifi) && ttls[vifi] && ttls[vifi] < 255) { + cache->mfc_un.res.ttls[vifi] = ttls[vifi]; + if (cache->mfc_un.res.minvif > vifi) + cache->mfc_un.res.minvif = vifi; + if (cache->mfc_un.res.maxvif <= vifi) + cache->mfc_un.res.maxvif = vifi + 1; + } + } +} + +static int mif6_add(struct mif6ctl *vifc, int mrtsock) +{ + int vifi = vifc->mif6c_mifi; + struct mif_device *v = &vif6_table[vifi]; + struct net_device *dev; + + /* Is vif busy ? */ + if (MIF_EXISTS(vifi)) + return -EADDRINUSE; + + switch (vifc->mif6c_flags) { + case 0: + dev = dev_get_by_index(&init_net, vifc->mif6c_pifi); + if (!dev) + return -EADDRNOTAVAIL; + dev_put(dev); + break; + default: + return -EINVAL; + } + + dev_set_allmulti(dev, 1); + + /* + * Fill in the VIF structures + */ + v->rate_limit = vifc->vifc_rate_limit; + v->flags = vifc->mif6c_flags; + if (!mrtsock) + v->flags |= VIFF_STATIC; + v->threshold = vifc->vifc_threshold; + v->bytes_in = 0; + v->bytes_out = 0; + v->pkt_in = 0; + v->pkt_out = 0; + v->link = dev->ifindex; + if (v->flags & MIFF_REGISTER) + v->link = dev->iflink; + + /* And finish update writing critical data */ + write_lock_bh(&mrt_lock); + dev_hold(dev); + v->dev = dev; + if (vifi + 1 > maxvif) + maxvif = vifi + 1; + write_unlock_bh(&mrt_lock); + return 0; +} + +static struct mfc6_cache *ip6mr_cache_find(struct in6_addr *origin, struct in6_addr *mcastgrp) +{ + int line = MFC6_HASH(mcastgrp, origin); + struct mfc6_cache *c; + + for (c = mfc6_cache_array[line]; c; c = c->next) { + if (ipv6_addr_equal(&c->mf6c_origin, origin) && + ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) + break; + } + return c; +} + +/* + * Allocate a multicast cache entry + */ +static struct mfc6_cache *ip6mr_cache_alloc(void) +{ + struct mfc6_cache *c = kmem_cache_alloc(mrt_cachep, GFP_KERNEL); + if (c == NULL) + return NULL; + memset(c, 0, sizeof(*c)); + c->mfc_un.res.minvif = MAXVIFS; + return c; +} + +static struct mfc6_cache *ip6mr_cache_alloc_unres(void) +{ + struct mfc6_cache *c = kmem_cache_alloc(mrt_cachep, GFP_ATOMIC); + if (c == NULL) + return NULL; + memset(c, 0, sizeof(*c)); + skb_queue_head_init(&c->mfc_un.unres.unresolved); + c->mfc_un.unres.expires = jiffies + 10 * HZ; + return c; +} + +/* + * A cache entry has gone into a resolved state from queued + */ + +static void ip6mr_cache_resolve(struct mfc6_cache *uc, struct mfc6_cache *c) +{ + struct sk_buff *skb; + + /* + * Play the pending entries through our router + */ + + while((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { + if (ipv6_hdr(skb)->version == 0) { + int err; + struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr)); + + if (ip6mr_fill_mroute(skb, c, NLMSG_DATA(nlh)) > 0) { + nlh->nlmsg_len = skb->tail - (u8 *)nlh; + } else { + nlh->nlmsg_type = NLMSG_ERROR; + nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr)); + skb_trim(skb, nlh->nlmsg_len); + ((struct nlmsgerr *)NLMSG_DATA(nlh))->error = -EMSGSIZE; + } + err = rtnl_unicast(skb, &init_net, NETLINK_CB(skb).pid); + } else + ip6_mr_forward(skb, c); + } +} + +/* + * Bounce a cache query up to pim6sd. We could use netlink for this but pim6sd + * expects the following bizarre scheme. + * + * Called under mrt_lock. + */ + +static int ip6mr_cache_report(struct sk_buff *pkt, vifi_t vifi, int assert) +{ + struct sk_buff *skb; + struct mrt6msg *msg; + int ret; + + skb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(*msg), GFP_ATOMIC); + + if (!skb) + return -ENOBUFS; + + /* I suppose that internal messages + * do not require checksums */ + + skb->ip_summed = CHECKSUM_UNNECESSARY; + + /* + * Copy the IP header + */ + + skb_put(skb, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb); + skb_copy_to_linear_data(skb, ipv6_hdr(pkt), sizeof(struct ipv6hdr)); + + /* + * Add our header + */ + skb_put(skb, sizeof(*msg)); + skb_reset_transport_header(skb); + msg = (struct mrt6msg *)skb_transport_header(skb); + + msg->im6_mbz = 0; + msg->im6_msgtype = assert; + msg->im6_mif = vifi; + msg->im6_pad = 0; + ipv6_addr_copy(&msg->im6_src, &ipv6_hdr(pkt)->saddr); + ipv6_addr_copy(&msg->im6_dst, &ipv6_hdr(pkt)->daddr); + + skb->dst = dst_clone(pkt->dst); + skb->ip_summed = CHECKSUM_UNNECESSARY; + + skb_pull(skb, sizeof(struct ipv6hdr)); + + if (mroute6_socket == NULL) { + kfree_skb(skb); + return -EINVAL; + } + + /* + * Deliver to user space multicast routing algorithms + */ + if ((ret = sock_queue_rcv_skb(mroute6_socket, skb)) < 0) { + if (net_ratelimit()) + printk(KERN_WARNING "mroute6: pending queue full, dropping entries.\n"); + kfree_skb(skb); + } + + return ret; +} + +/* + * Queue a packet for resolution. It gets locked cache entry! + */ + +static int +ip6mr_cache_unresolved(vifi_t vifi, struct sk_buff *skb) +{ + int err; + struct mfc6_cache *c; + + spin_lock_bh(&mfc_unres_lock); + for (c = mfc_unres_queue; c; c = c->next) { + if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) && + ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) + break; + } + + if (c == NULL) { + /* + * Create a new entry if allowable + */ + + if (atomic_read(&cache_resolve_queue_len) >= 10 || + (c = ip6mr_cache_alloc_unres()) == NULL) { + spin_unlock_bh(&mfc_unres_lock); + + kfree_skb(skb); + return -ENOBUFS; + } + + /* + * Fill in the new cache entry + */ + c->mf6c_parent = -1; + c->mf6c_origin = ipv6_hdr(skb)->saddr; + c->mf6c_mcastgrp = ipv6_hdr(skb)->daddr; + + /* + * Reflect first query at pim6sd + */ + if ((err = ip6mr_cache_report(skb, vifi, MRT6MSG_NOCACHE)) < 0) { + /* If the report failed throw the cache entry + out - Brad Parker + */ + spin_unlock_bh(&mfc_unres_lock); + + kmem_cache_free(mrt_cachep, c); + kfree_skb(skb); + return err; + } + + atomic_inc(&cache_resolve_queue_len); + c->next = mfc_unres_queue; + mfc_unres_queue = c; + + ipmr_do_expire_process(1); + } + + /* + * See if we can append the packet + */ + if (c->mfc_un.unres.unresolved.qlen > 3) { + kfree_skb(skb); + err = -ENOBUFS; + } else { + skb_queue_tail(&c->mfc_un.unres.unresolved, skb); + err = 0; + } + + spin_unlock_bh(&mfc_unres_lock); + return err; +} + +/* + * MFC6 cache manipulation by user space + */ + +static int ip6mr_mfc_delete(struct mf6cctl *mfc) +{ + int line; + struct mfc6_cache *c, **cp; + + line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); + + for (cp = &mfc6_cache_array[line]; (c = *cp) != NULL; cp = &c->next) { + if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && + ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) { + write_lock_bh(&mrt_lock); + *cp = c->next; + write_unlock_bh(&mrt_lock); + + kmem_cache_free(mrt_cachep, c); + return 0; + } + } + return -ENOENT; +} + +static int ip6mr_device_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *dev = ptr; + struct mif_device *v; + int ct; + + if (dev_net(dev) != &init_net) + return NOTIFY_DONE; + + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + + v = &vif6_table[0]; + for (ct = 0; ct < maxvif; ct++, v++) { + if (v->dev == dev) + mif6_delete(ct); + } + return NOTIFY_DONE; +} + +static struct notifier_block ip6_mr_notifier = { + .notifier_call = ip6mr_device_event +}; + +/* + * Setup for IP multicast routing + */ + +void __init ip6_mr_init(void) +{ + mrt_cachep = kmem_cache_create("ip6_mrt_cache", + sizeof(struct mfc6_cache), + 0, SLAB_HWCACHE_ALIGN, + NULL); + if (!mrt_cachep) + panic("cannot allocate ip6_mrt_cache"); + + setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0); + register_netdevice_notifier(&ip6_mr_notifier); +#ifdef CONFIG_PROC_FS + proc_net_fops_create(&init_net, "ip6_mr_vif", 0, &ip6mr_vif_fops); + proc_net_fops_create(&init_net, "ip6_mr_cache", 0, &ip6mr_mfc_fops); +#endif +} + + +static int ip6mr_mfc_add(struct mf6cctl *mfc, int mrtsock) +{ + int line; + struct mfc6_cache *uc, *c, **cp; + unsigned char ttls[MAXVIFS]; + int i; + + memset(ttls, 255, MAXVIFS); + for (i = 0; i < MAXVIFS; i++) { + if (IF_ISSET(i, &mfc->mf6cc_ifset)) + ttls[i] = 1; + + } + + line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr); + + for (cp = &mfc6_cache_array[line]; (c = *cp) != NULL; cp = &c->next) { + if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) && + ipv6_addr_equal(&c->mf6c_mcastgrp, &mfc->mf6cc_mcastgrp.sin6_addr)) + break; + } + + if (c != NULL) { + write_lock_bh(&mrt_lock); + c->mf6c_parent = mfc->mf6cc_parent; + ip6mr_update_thresholds(c, ttls); + if (!mrtsock) + c->mfc_flags |= MFC_STATIC; + write_unlock_bh(&mrt_lock); + return 0; + } + + if (!ipv6_addr_is_multicast(&mfc->mf6cc_mcastgrp.sin6_addr)) + return -EINVAL; + + c = ip6mr_cache_alloc(); + if (c == NULL) + return -ENOMEM; + + c->mf6c_origin = mfc->mf6cc_origin.sin6_addr; + c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr; + c->mf6c_parent = mfc->mf6cc_parent; + ip6mr_update_thresholds(c, ttls); + if (!mrtsock) + c->mfc_flags |= MFC_STATIC; + + write_lock_bh(&mrt_lock); + c->next = mfc6_cache_array[line]; + mfc6_cache_array[line] = c; + write_unlock_bh(&mrt_lock); + + /* + * Check to see if we resolved a queued list. If so we + * need to send on the frames and tidy up. + */ + spin_lock_bh(&mfc_unres_lock); + for (cp = &mfc_unres_queue; (uc = *cp) != NULL; + cp = &uc->next) { + if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) && + ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) { + *cp = uc->next; + if (atomic_dec_and_test(&cache_resolve_queue_len)) + del_timer(&ipmr_expire_timer); + break; + } + } + spin_unlock_bh(&mfc_unres_lock); + + if (uc) { + ip6mr_cache_resolve(uc, c); + kmem_cache_free(mrt_cachep, uc); + } + return 0; +} + +/* + * Close the multicast socket, and clear the vif tables etc + */ + +static void mroute_clean_tables(struct sock *sk) +{ + int i; + + /* + * Shut down all active vif entries + */ + for (i = 0; i < maxvif; i++) { + if (!(vif6_table[i].flags & VIFF_STATIC)) + mif6_delete(i); + } + + /* + * Wipe the cache + */ + for (i = 0; i < ARRAY_SIZE(mfc6_cache_array); i++) { + struct mfc6_cache *c, **cp; + + cp = &mfc6_cache_array[i]; + while ((c = *cp) != NULL) { + if (c->mfc_flags & MFC_STATIC) { + cp = &c->next; + continue; + } + write_lock_bh(&mrt_lock); + *cp = c->next; + write_unlock_bh(&mrt_lock); + + kmem_cache_free(mrt_cachep, c); + } + } + + if (atomic_read(&cache_resolve_queue_len) != 0) { + struct mfc6_cache *c; + + spin_lock_bh(&mfc_unres_lock); + while (mfc_unres_queue != NULL) { + c = mfc_unres_queue; + mfc_unres_queue = c->next; + spin_unlock_bh(&mfc_unres_lock); + + ip6mr_destroy_unres(c); + + spin_lock_bh(&mfc_unres_lock); + } + spin_unlock_bh(&mfc_unres_lock); + } +} + +static int ip6mr_sk_init(struct sock *sk) +{ + int err = 0; + + rtnl_lock(); + write_lock_bh(&mrt_lock); + if (likely(mroute6_socket == NULL)) + mroute6_socket = sk; + else + err = -EADDRINUSE; + write_unlock_bh(&mrt_lock); + + rtnl_unlock(); + + return err; +} + +int ip6mr_sk_done(struct sock *sk) +{ + int err = 0; + + rtnl_lock(); + if (sk == mroute6_socket) { + write_lock_bh(&mrt_lock); + mroute6_socket = NULL; + write_unlock_bh(&mrt_lock); + + mroute_clean_tables(sk); + } else + err = -EACCES; + rtnl_unlock(); + + return err; +} + +/* + * Socket options and virtual interface manipulation. The whole + * virtual interface system is a complete heap, but unfortunately + * that's how BSD mrouted happens to think. Maybe one day with a proper + * MOSPF/PIM router set up we can clean this up. + */ + +int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int optlen) +{ + int ret; + struct mif6ctl vif; + struct mf6cctl mfc; + mifi_t mifi; + + if (optname != MRT6_INIT) { + if (sk != mroute6_socket && !capable(CAP_NET_ADMIN)) + return -EACCES; + } + + switch (optname) { + case MRT6_INIT: + if (sk->sk_type != SOCK_RAW || + inet_sk(sk)->num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + if (optlen < sizeof(int)) + return -EINVAL; + + return ip6mr_sk_init(sk); + + case MRT6_DONE: + return ip6mr_sk_done(sk); + + case MRT6_ADD_MIF: + if (optlen < sizeof(vif)) + return -EINVAL; + if (copy_from_user(&vif, optval, sizeof(vif))) + return -EFAULT; + if (vif.mif6c_mifi >= MAXVIFS) + return -ENFILE; + rtnl_lock(); + ret = mif6_add(&vif, sk == mroute6_socket); + rtnl_unlock(); + return ret; + + case MRT6_DEL_MIF: + if (optlen < sizeof(mifi_t)) + return -EINVAL; + if (copy_from_user(&mifi, optval, sizeof(mifi_t))) + return -EFAULT; + rtnl_lock(); + ret = mif6_delete(mifi); + rtnl_unlock(); + return ret; + + /* + * Manipulate the forwarding caches. These live + * in a sort of kernel/user symbiosis. + */ + case MRT6_ADD_MFC: + case MRT6_DEL_MFC: + if (optlen < sizeof(mfc)) + return -EINVAL; + if (copy_from_user(&mfc, optval, sizeof(mfc))) + return -EFAULT; + rtnl_lock(); + if (optname == MRT6_DEL_MFC) + ret = ip6mr_mfc_delete(&mfc); + else + ret = ip6mr_mfc_add(&mfc, sk == mroute6_socket); + rtnl_unlock(); + return ret; + + /* + * Spurious command, or MRT_VERSION which you cannot + * set. + */ + default: + return -ENOPROTOOPT; + } +} + +/* + * Getsock opt support for the multicast routing system. + */ + +int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, + int __user *optlen) +{ + int olr; + int val; + + switch (optname) { + case MRT6_VERSION: + val = 0x0305; + break; + default: + return -ENOPROTOOPT; + } + + if (get_user(olr, optlen)) + return -EFAULT; + + olr = min_t(int, olr, sizeof(int)); + if (olr < 0) + return -EINVAL; + + if (put_user(olr, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, olr)) + return -EFAULT; + return 0; +} + +/* + * The IP multicast ioctl support routines. + */ + +int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) +{ + struct sioc_sg_req6 sr; + struct sioc_mif_req6 vr; + struct mif_device *vif; + struct mfc6_cache *c; + + switch (cmd) { + case SIOCGETMIFCNT_IN6: + if (copy_from_user(&vr, arg, sizeof(vr))) + return -EFAULT; + if (vr.mifi >= maxvif) + return -EINVAL; + read_lock(&mrt_lock); + vif = &vif6_table[vr.mifi]; + if (MIF_EXISTS(vr.mifi)) { + vr.icount = vif->pkt_in; + vr.ocount = vif->pkt_out; + vr.ibytes = vif->bytes_in; + vr.obytes = vif->bytes_out; + read_unlock(&mrt_lock); + + if (copy_to_user(arg, &vr, sizeof(vr))) + return -EFAULT; + return 0; + } + read_unlock(&mrt_lock); + return -EADDRNOTAVAIL; + case SIOCGETSGCNT_IN6: + if (copy_from_user(&sr, arg, sizeof(sr))) + return -EFAULT; + + read_lock(&mrt_lock); + c = ip6mr_cache_find(&sr.src.sin6_addr, &sr.grp.sin6_addr); + if (c) { + sr.pktcnt = c->mfc_un.res.pkt; + sr.bytecnt = c->mfc_un.res.bytes; + sr.wrong_if = c->mfc_un.res.wrong_if; + read_unlock(&mrt_lock); + + if (copy_to_user(arg, &sr, sizeof(sr))) + return -EFAULT; + return 0; + } + read_unlock(&mrt_lock); + return -EADDRNOTAVAIL; + default: + return -ENOIOCTLCMD; + } +} + + +static inline int ip6mr_forward2_finish(struct sk_buff *skb) +{ + /* XXX stats */ + return dst_output(skb); +} + +/* + * Processing handlers for ip6mr_forward + */ + +static int ip6mr_forward2(struct sk_buff *skb, struct mfc6_cache *c, int vifi) +{ + struct ipv6hdr *ipv6h; + struct mif_device *vif = &vif6_table[vifi]; + struct net_device *dev; + struct dst_entry *dst; + struct flowi fl; + + if (vif->dev == NULL) + goto out_free; + + ipv6h = ipv6_hdr(skb); + + fl = (struct flowi) { + .oif = vif->link, + .nl_u = { .ip6_u = + { .daddr = ipv6h->daddr, } + } + }; + + dst = ip6_route_output(&init_net, NULL, &fl); + if (!dst) + goto out_free; + + dst_release(skb->dst); + skb->dst = dst; + + /* + * RFC1584 teaches, that DVMRP/PIM router must deliver packets locally + * not only before forwarding, but after forwarding on all output + * interfaces. It is clear, if mrouter runs a multicasting + * program, it should receive packets not depending to what interface + * program is joined. + * If we will not make it, the program will have to join on all + * interfaces. On the other hand, multihoming host (or router, but + * not mrouter) cannot join to more than one interface - it will + * result in receiving multiple packets. + */ + dev = vif->dev; + skb->dev = dev; + vif->pkt_out++; + vif->bytes_out += skb->len; + + /* We are about to write */ + /* XXX: extension headers? */ + if (skb_cow(skb, sizeof(*ipv6h) + LL_RESERVED_SPACE(dev))) + goto out_free; + + ipv6h = ipv6_hdr(skb); + ipv6h->hop_limit--; + + IP6CB(skb)->flags |= IP6SKB_FORWARDED; + + return NF_HOOK(PF_INET6, NF_INET_FORWARD, skb, skb->dev, dev, + ip6mr_forward2_finish); + +out_free: + kfree_skb(skb); + return 0; +} + +static int ip6mr_find_vif(struct net_device *dev) +{ + int ct; + for (ct = maxvif - 1; ct >= 0; ct--) { + if (vif6_table[ct].dev == dev) + break; + } + return ct; +} + +static int ip6_mr_forward(struct sk_buff *skb, struct mfc6_cache *cache) +{ + int psend = -1; + int vif, ct; + + vif = cache->mf6c_parent; + cache->mfc_un.res.pkt++; + cache->mfc_un.res.bytes += skb->len; + + vif6_table[vif].pkt_in++; + vif6_table[vif].bytes_in += skb->len; + + /* + * Forward the frame + */ + for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) { + if (ipv6_hdr(skb)->hop_limit > cache->mfc_un.res.ttls[ct]) { + if (psend != -1) { + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + if (skb2) + ip6mr_forward2(skb2, cache, psend); + } + psend = ct; + } + } + if (psend != -1) { + ip6mr_forward2(skb, cache, psend); + return 0; + } + + kfree_skb(skb); + return 0; +} + + +/* + * Multicast packets for forwarding arrive here + */ + +int ip6_mr_input(struct sk_buff *skb) +{ + struct mfc6_cache *cache; + + read_lock(&mrt_lock); + cache = ip6mr_cache_find(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr); + + /* + * No usable cache entry + */ + if (cache == NULL) { + int vif; + + vif = ip6mr_find_vif(skb->dev); + if (vif >= 0) { + int err = ip6mr_cache_unresolved(vif, skb); + read_unlock(&mrt_lock); + + return err; + } + read_unlock(&mrt_lock); + kfree_skb(skb); + return -ENODEV; + } + + ip6_mr_forward(skb, cache); + + read_unlock(&mrt_lock); + + return 0; +} + + +static int +ip6mr_fill_mroute(struct sk_buff *skb, struct mfc6_cache *c, struct rtmsg *rtm) +{ + int ct; + struct rtnexthop *nhp; + struct net_device *dev = vif6_table[c->mf6c_parent].dev; + u8 *b = skb->tail; + struct rtattr *mp_head; + + if (dev) + RTA_PUT(skb, RTA_IIF, 4, &dev->ifindex); + + mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0)); + + for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { + if (c->mfc_un.res.ttls[ct] < 255) { + if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) + goto rtattr_failure; + nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); + nhp->rtnh_flags = 0; + nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; + nhp->rtnh_ifindex = vif6_table[ct].dev->ifindex; + nhp->rtnh_len = sizeof(*nhp); + } + } + mp_head->rta_type = RTA_MULTIPATH; + mp_head->rta_len = skb->tail - (u8 *)mp_head; + rtm->rtm_type = RTN_MULTICAST; + return 1; + +rtattr_failure: + nlmsg_trim(skb, b); + return -EMSGSIZE; +} + +int ip6mr_get_route(struct sk_buff *skb, struct rtmsg *rtm, int nowait) +{ + int err; + struct mfc6_cache *cache; + struct rt6_info *rt = (struct rt6_info *)skb->dst; + + read_lock(&mrt_lock); + cache = ip6mr_cache_find(&rt->rt6i_src.addr, &rt->rt6i_dst.addr); + + if (!cache) { + struct sk_buff *skb2; + struct ipv6hdr *iph; + struct net_device *dev; + int vif; + + if (nowait) { + read_unlock(&mrt_lock); + return -EAGAIN; + } + + dev = skb->dev; + if (dev == NULL || (vif = ip6mr_find_vif(dev)) < 0) { + read_unlock(&mrt_lock); + return -ENODEV; + } + + /* really correct? */ + skb2 = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC); + if (!skb2) { + read_unlock(&mrt_lock); + return -ENOMEM; + } + + skb_reset_transport_header(skb2); + + skb_put(skb2, sizeof(struct ipv6hdr)); + skb_reset_network_header(skb2); + + iph = ipv6_hdr(skb2); + iph->version = 0; + iph->priority = 0; + iph->flow_lbl[0] = 0; + iph->flow_lbl[1] = 0; + iph->flow_lbl[2] = 0; + iph->payload_len = 0; + iph->nexthdr = IPPROTO_NONE; + iph->hop_limit = 0; + ipv6_addr_copy(&iph->saddr, &rt->rt6i_src.addr); + ipv6_addr_copy(&iph->daddr, &rt->rt6i_dst.addr); + + err = ip6mr_cache_unresolved(vif, skb2); + read_unlock(&mrt_lock); + + return err; + } + + if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY)) + cache->mfc_flags |= MFC_NOTIFY; + + err = ip6mr_fill_mroute(skb, cache, rtm); + read_unlock(&mrt_lock); + return err; +} + diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 4195ac92345e..99624109c010 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -33,6 +33,7 @@ #include #include #include +#include #include #include #include @@ -118,6 +119,9 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, valbool = (val!=0); + if (ip6_mroute_opt(optname)) + return ip6_mroute_setsockopt(sk, optname, optval, optlen); + lock_sock(sk); switch (optname) { @@ -790,6 +794,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, int len; int val; + if (ip6_mroute_opt(optname)) + return ip6_mroute_getsockopt(sk, optname, optval, optlen); + if (get_user(len, optlen)) return -EFAULT; switch (optname) { diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index aae6cedf1709..088b80b4ce74 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -53,6 +53,7 @@ #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) #include #endif +#include #include #include @@ -1135,7 +1136,11 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) } default: +#ifdef CONFIG_IPV6_MROUTE + return ip6mr_ioctl(sk, cmd, (void __user *)arg); +#else return -ENOIOCTLCMD; +#endif } } @@ -1143,7 +1148,7 @@ static void rawv6_close(struct sock *sk, long timeout) { if (inet_sk(sk)->num == IPPROTO_RAW) ip6_ra_control(sk, -1, NULL); - + ip6mr_sk_done(sk); sk_common_release(sk); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index cd82b6db35ff..3c314d5f46c6 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -36,6 +36,7 @@ #include #include #include +#include #include #include #include @@ -2106,7 +2107,7 @@ static inline size_t rt6_nlmsg_size(void) static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, struct in6_addr *dst, struct in6_addr *src, int iif, int type, u32 pid, u32 seq, - int prefix, unsigned int flags) + int prefix, int nowait, unsigned int flags) { struct rtmsg *rtm; struct nlmsghdr *nlh; @@ -2166,9 +2167,24 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, } else if (rtm->rtm_src_len) NLA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr); #endif - if (iif) - NLA_PUT_U32(skb, RTA_IIF, iif); - else if (dst) { + if (iif) { +#ifdef CONFIG_IPV6_MROUTE + if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) { + int err = ip6mr_get_route(skb, rtm, nowait); + if (err <= 0) { + if (!nowait) { + if (err == 0) + return 0; + goto nla_put_failure; + } else { + if (err == -EMSGSIZE) + goto nla_put_failure; + } + } + } else +#endif + NLA_PUT_U32(skb, RTA_IIF, iif); + } else if (dst) { struct in6_addr saddr_buf; if (ipv6_dev_get_saddr(ip6_dst_idev(&rt->u.dst)->dev, dst, 0, &saddr_buf) == 0) @@ -2211,7 +2227,7 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg) return rt6_fill_node(arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq, - prefix, NLM_F_MULTI); + prefix, 0, NLM_F_MULTI); } static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) @@ -2277,7 +2293,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void err = rt6_fill_node(skb, rt, &fl.fl6_dst, &fl.fl6_src, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).pid, - nlh->nlmsg_seq, 0, 0); + nlh->nlmsg_seq, 0, 0, 0); if (err < 0) { kfree_skb(skb); goto errout; @@ -2303,7 +2319,7 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) goto errout; err = rt6_fill_node(skb, rt, NULL, NULL, 0, - event, info->pid, seq, 0, 0); + event, info->pid, seq, 0, 0, 0); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); -- cgit v1.2.3